pith. sign in

arxiv: 2606.19316 · v1 · pith:UFOA4HEFnew · submitted 2026-06-17 · 💻 cs.CV

NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field

Chong Bao , Yuan Li , Bangbang Yang , Yujun Shen , Hujun Bao , Zhaopeng Cui , Yinda Zhang , Guofeng Zhang This is my paper

Pith reviewed 2026-06-26 21:20 UTC · model grok-4.3

classification 💻 cs.CV
keywords neural radiance fieldvolumetric editingmesh-based representationdisentangled codes3D scene editingtexture editingsemantic editingimplicit field
0
0 comments X

The pith

A mesh-based representation encodes neural radiance fields with separate geometry, texture and semantic codes on vertices to support multiple editing operations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a mesh-based way to store neural radiance fields by placing disentangled codes for geometry, texture and semantics directly on mesh vertices. This design enables mesh-guided shape changes, targeted texture swaps, fills and paints, plus semantic-driven edits that prior implicit methods could not handle easily. Supporting techniques include local space parameterization for better quality, learnable modification colors for texture fidelity, spatial-aware optimization for precision, and semantic-aided selection to simplify region choice. A sympathetic reader would care because the approach combines the flexibility of implicit fields with controllable mesh edits, making 3D content manipulation more practical.

Core claim

We present a novel mesh-based representation by encoding the neural radiance field with disentangled geometry, texture, and semantic codes on mesh vertices, which empowers a set of efficient and comprehensive editing functionalities, including mesh-guided geometry editing, designated texture editing with texture swapping, filling and painting operations, and semantic-guided editing. The work develops local space parameterization to enhance rendering quality and training stability, a learnable modification color on vertices to improve texture editing fidelity, a spatial-aware optimization strategy for precise texture edits, and semantic-aided region selection to reduce annotation effort.

What carries the argument

Disentangled geometry, texture and semantic codes placed on mesh vertices, which carry independent editing operations while preserving the underlying implicit field.

If this is right

  • Mesh-guided geometry editing can be applied directly while keeping rendering quality intact.
  • Texture swapping, filling and painting become feasible on designated regions with improved fidelity.
  • Semantic-guided editing reduces the need for manual annotation of implicit fields.
  • The representation maintains high quality on both real and synthetic data across the listed edit types.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The vertex-level disentanglement may make it simpler to combine edits from multiple independent sources than entangled field representations allow.
  • The local parameterization step could transfer to other mesh-based implicit models to improve their training stability.
  • Adding further vertex attributes such as material or lighting codes would be a direct next step for broader editing control.

Load-bearing premise

The local space parameterization, learnable modification color, spatial-aware optimization and semantic-aided region selection will deliver high-fidelity edits and stable training without artifacts or post-hoc fixes.

What would settle it

Apply the texture painting operation to a held-out real scene and check whether novel-view renderings of the painted region show seams, color drift or loss of detail relative to the intended edit.

Figures

Figures reproduced from arXiv: 2606.19316 by Bangbang Yang, Chong Bao, Guofeng Zhang, Hujun Bao, Yinda Zhang, Yuan Li, Yujun Shen, Zhaopeng Cui.

Figure 1
Figure 1. Figure 1: We present a novel representation for volumetric neural rendering, which encodes the neural implicit field with [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview. We encode the neural radiance field on a mesh-based scaffold, where each vertex maintains a geometry, texture, and semantic code l g ,l t ,l s and a modification color c m for high-fidelity texture editing. For a query point x along a casted camera ray, we retrieve codes and local indicators from the nearby mesh vertices, and forward to the geometry/radiance decoder to obtain density value σk and… view at source ↗
Figure 3
Figure 3. Figure 3: Mesh-guided Geometry editing. By simply deform￾ing the corresponding mesh, the change will synchronously take effect on the implicit field, and the rendered object will also be deformed accordingly. methods [74, 87, 89] which directly function on the global coordinate x, we instead forward the local geometry code l g k , local texture code l t k along with the local indicator vector hk = (pk, wk) to the ge… view at source ↗
Figure 4
Figure 4. Figure 4: Designatable texture editing. By exchanging texture codes (and decoders), our representation delivers various texture editing pipelines on the neural implicit field. material properties. We propose to mimic such pipelines by introducing a designatable texture editing, where the selection of mesh vertices is used to precisely guide the texture editing on the region of interest. The core step of our texture … view at source ↗
Figure 5
Figure 5. Figure 5: Semantic-guided texture editing. Users select a semantic region of the object by clicking from a single viewpoint and edit the texture of the selected 3D region. tors) are untouched in the target object, the modified color c ′ k becomes: c ′ k = FR  l t ′ k , hk, d, nk  + c m′ k . (7) 2) Texture filling by filling a target object area with repeated textures from a pre-captured model (e.g., assigning part… view at source ↗
Figure 6
Figure 6. Figure 6: Semantic-driven geometry editing. Users can select a semantic region of the object by clicking from a single viewpoint and decomposing its geometry from the object. users to quickly select semantically consistent 3D segments through simple point selection on a single view. Fortunately, many open-vocabulary segmentation tools [6, 28] have been released. By leveraging open-vocabulary segmentation models [6, … view at source ↗
Figure 9
Figure 9. Figure 9: Texture swapping. We present 2 examples of texture swap￾ping in [PITH_FULL_IMAGE:figures/full_fig_p009_9.png] view at source ↗
Figure 7
Figure 7. Figure 7: Geometry editing. We show examples of mesh-guided geometry editing in (a) and physical simulation results in (c), and compare with NeuMesh [83] in (b). and texture in two spaces, and the disentangled texture representation is seamlessly integrated into new shapes. Texture filling. We show 2 examples of texture filling in [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Editing results comparison. We show texture editing examples on the DTU dataset [20] and the NeRF 360◦ Synthetic dataset [40]. Resolution Num. Vertices PSNR↑ SSIM↑ LPIPS↓(Vgg) 100 128.3K 30.352 0.936 0.080 200 215.8K 31.900 0.952 0.058 300 307.5K 32.324 0.955 0.053 TABLE 4: Ablation on mesh resolution. We compare the rendering quality with different marching cube resolutions on NeRF 360◦ synthetic dataset … view at source ↗
Figure 9
Figure 9. Figure 9: Texture editing results. We show more texture painting and semantic-guided editing examples on the DTU dataset [20] and the NeRF 360◦ Synthetic dataset [40]. 0 2 4 6 8 10 31.75 32.00 32.25 32.50 Queried vertex number (N) Avg. PSNR PNSR w.r.t. KNN 0 2 4 6 8 10 0.951 0.953 0.955 0.957 Queried vertex number (N) Avg. SSIM SSIM w.r.t. KNN 0 2 4 6 8 10 0.050 0.054 0.058 0.062 Queried vertex number (N) Avg. LPIPS… view at source ↗
Figure 10
Figure 10. Figure 10: Ablation on KNN searching. We compare rendering quality with different K-Nearest Neighboring Searching numbers. PSNR↑ SSIM↑ LPIPS↓(Vgg) w/ distillation 32.2740 0.9551 0.0537 ours 32.324 0.9550 0.0534 TABLE 5: Ablation on distillation. We compare the render￾ing quality between training with distillation (w/ distilla￾tion) and training without distillation (ours) on NeRF 360◦ synthetic dataset [40]. coder. … view at source ↗
Figure 11
Figure 11. Figure 11: Ablation on texture swapping. We compare dif￾ferent texture-swapping qualities. Models without normal information cannot produce authentic golden reflections based on object geometry. Original & Canvas Ours w/o cm Ours [PITH_FULL_IMAGE:figures/full_fig_p013_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Ablation on painting. We compare different paint￾ing qualities. Model without modification color c m pro￾duces noisy results after finetuning for the same iterations compared to our method. Hybrid Editing on Original Object Our Rendered Edited Objects [PITH_FULL_IMAGE:figures/full_fig_p013_12.png] view at source ↗
Figure 14
Figure 14. Figure 14: Hybrid editing. We show examples of hybrid object editing by combining multiple editing operations. demonstrate versatile editing capabilities of our representa￾tion on both real-world and synthetic data. In the synthetic chair scene, we bend the chair’s arms and legs while swap- [PITH_FULL_IMAGE:figures/full_fig_p013_14.png] view at source ↗
Figure 13
Figure 13. Figure 13: Ablation on the size of our model. We show the quantitative ablation on the size of MLP decoders and neural codes. The evaluated sizes of MLP decoders are 32, 64, 128. The evaluated size of geometry and texture codes are (#Geo.+#Tex.): 3+9, 6+15, and 12+24. PSNR↑ SSIM↑ LPIPS↓(Alex) BakedSDF* [88] 23.31 0.651 0.277 Ours 26.34 0.731 0.216 TABLE 8: Quantitative comparison. We show quantitative comparisons wi… view at source ↗
Figure 15
Figure 15. Figure 15: Qualitative comparison. We show qualitative com￾parisons with BakedSDF* [88] on Mip-NeRF 360 [1] dataset. Texture Swapping. Texture swapping requires that the tem￾plate and edited region possess similar shapes, ensuring proper alignment of the edited region with the template in Euclidean space. This ensures the accurate retrieval of the corresponding template texture codes for each modified vertex, thereb… view at source ↗
read the original abstract

Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods for editing purposes offer limited functionalities, e.g., rigid transformation and category-specific editing. In this paper, we present a novel mesh-based representation by encoding the neural radiance field with disentangled geometry, texture, and semantic codes on mesh vertices, which empowers a set of efficient and comprehensive editing functionalities, including mesh-guided geometry editing, designated texture editing with texture swapping, filling and painting operations, and semantic-guided editing. To this end, we develop several techniques including a novel local space parameterization to enhance rendering quality and training stability, a learnable modification color on vertex to improve the fidelity of texture editing, a spatial-aware optimization strategy to realize precise texture editing, and a semantic-aided region selection to ease the laborious annotation of implicit field editing. Extensive experiments and editing examples on both real and synthetic datasets demonstrate the superiority of our method on representation quality and editing ability. Project page: https://zju3dv.github.io/neumeshplusplus/

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes NeuMesh++, a mesh-based implicit representation that encodes neural radiance fields using disentangled geometry, texture, and semantic codes attached to mesh vertices. This enables a range of editing operations: mesh-guided geometry editing, designated texture editing (swapping, filling, painting), and semantic-guided editing. Supporting components include local space parameterization, learnable modification color on vertices, spatial-aware optimization, and semantic-aided region selection. The authors assert that these yield high-fidelity edits and superior representation quality, validated by extensive experiments on real and synthetic datasets.

Significance. If the empirical claims hold with proper quantitative support, the work could provide a practical bridge between explicit mesh control and implicit field flexibility, expanding editing capabilities beyond rigid transforms or category-specific methods in neural rendering.

major comments (1)
  1. Abstract: the central claim of superiority 'via extensive experiments' is asserted without any quantitative results, baselines, error bars, ablation tables, or method implementation details, so the load-bearing empirical support for the editing functionalities cannot be assessed from the provided text.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the detailed review and the opportunity to clarify our work. We address the single major comment below.

read point-by-point responses

  1. Referee: [—] Abstract: the central claim of superiority 'via extensive experiments' is asserted without any quantitative results, baselines, error bars, ablation tables, or method implementation details, so the load-bearing empirical support for the editing functionalities cannot be assessed from the provided text.

    Authors: We acknowledge that the abstract, as a concise summary, does not include specific quantitative numbers, baselines, or ablation details. These elements are presented in full in the Experiments section of the manuscript, including quantitative comparisons on representation quality (e.g., PSNR/SSIM metrics), editing fidelity, ablation studies, and implementation specifics. However, to improve accessibility of the central claim from the abstract alone, we will revise the abstract to incorporate one or two key quantitative highlights demonstrating the reported superiority. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper presents a novel mesh-based implicit representation with disentangled vertex codes plus four supporting techniques (local space parameterization, learnable modification color, spatial-aware optimization, semantic-aided selection). Central claims rest on empirical results from experiments on real and synthetic datasets rather than any derivation chain. No equations, fitted parameters renamed as predictions, self-definitional loops, or load-bearing self-citations appear in the provided text. The method is self-contained via external empirical validation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No specific free parameters, axioms, or invented entities can be identified from the abstract alone; the representation relies on standard neural implicit field assumptions whose details are not provided.

pith-pipeline@v0.9.1-grok · 5749 in / 1150 out tokens · 34516 ms · 2026-06-26T21:20:20.603466+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

98 extracted references · 14 canonical work pages · 3 internal anchors

  1. [1]

    Real-Time Rendering

    Tomas Akenine-Moller, Eric Haines, and Naty Hoffman. Real-Time Rendering. AK Peters/crc Press, 2019

    2019

  2. [2]

    Geneavatar: Generic expression-aware volumetric head avatar editing from a single image

    Chong Bao, Yinda Zhang, Yuan Li, Xiyu Zhang, Bangbang Yang, Hujun Bao, Marc Pollefeys, Guofeng Zhang, and Zhaopeng Cui. Geneavatar: Generic expression-aware volumetric head avatar editing from a single image. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8952–8963, 2024

    2024

  3. [3]

    Mip-nerf 360: Unbounded anti-aliased neural radiance fields

    Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. InProceedings of the IEEE/CVF conference on computer vision and pattern recogni- tion, pages 5470–5479, 2022

    2022

  4. [4]

    Blender. Blender. https://www.blender.org/, 2023. Ac- cessed: 2023-12

    2023

  5. [5]

    NeRD: Neural Reflectance Decomposition from Image Collections

    Mark Boss, Raphael Braun, Varun Jampani, Jonathan T Barron, Ce Liu, and Hendrik Lensch. NeRD: Neural Reflectance Decomposition from Image Collections. In Proceedings of the IEEE/CVF International Conference on Com- puter Vision, pages 12684–12694, 2021

    2021

  6. [6]

    Emerging properties in self-supervised vision transform- ers

    Mathilde Caron, Hugo Touvron, Ishan Misra, Herv ´e J´egou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. Emerging properties in self-supervised vision transform- ers. InProceedings of the International Conference on Computer Vision (ICCV), 2021

    2021

  7. [7]

    Sofgan: A portrait image generator with dynamic styling.ACM Transactions on Graphics (TOG), 41(1):1–26, 2022

    Anpei Chen, Ruiyang Liu, Ling Xie, Zhang Chen, Hao Su, and Jingyi Yu. Sofgan: A portrait image generator with dynamic styling.ACM Transactions on Graphics (TOG), 41(1):1–26, 2022

    2022

  8. [8]

    Mvsnerf: Fast generalizable radiance field reconstruction from multi- view stereo

    Anpei Chen, Zexiang Xu, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, and Hao Su. Mvsnerf: Fast generalizable radiance field reconstruction from multi- view stereo. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 14124–14133, 2021

    2021

  9. [9]

    Neural Volume Render- ing: NeRF And Beyond.arXiv preprint arXiv:2101.05204, 2020

    Frank Dellaert and Lin Yen-Chen. Neural Volume Render- ing: NeRF And Beyond.arXiv preprint arXiv:2101.05204, 2020

    work page arXiv 2020

  10. [10]

    Deformed Im- plicit Field: Modeling 3D Shapes with Learned Dense Correspondence

    Yu Deng, Jiaolong Yang, and Xin Tong. Deformed Im- plicit Field: Modeling 3D Shapes with Learned Dense Correspondence. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10286– 10296, 2021

    2021

  11. [11]

    A density-based algorithm for discovering clusters in large spatial databases with noise

    Martin Ester, Hans-Peter Kriegel, J ¨org Sander, Xiaowei Xu, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. Inkdd, volume 96, pages 226–231, 1996

    1996

  12. [12]

    Unified implicit neural styl- ization

    Zhiwen Fan, Yifan Jiang, Peihao Wang, Xinyu Gong, Dejia Xu, and Zhangyang Wang. Unified implicit neural styl- ization. InEuropean Conference on Computer Vision, pages 636–654. Springer, 2022

    2022

  13. [13]

    Deferred Neural Lighting: Free-Viewpoint Relighting from Unstructured Photographs.ACM Transac- tions on Graphics (TOG), 39(6):1–15, 2020

    Duan Gao, Guojun Chen, Yue Dong, Pieter Peers, Kun Xu, and Xin Tong. Deferred Neural Lighting: Free-Viewpoint Relighting from Unstructured Photographs.ACM Transac- tions on Graphics (TOG), 39(6):1–15, 2020

    2020

  14. [14]

    A Papier-m ˆach´e Approach to Learning 3D Surface Generation

    Thibault Groueix, Matthew Fisher, Vladimir G Kim, Bryan C Russell, and Mathieu Aubry. A Papier-m ˆach´e Approach to Learning 3D Surface Generation. InProceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 216–224, 2018

    2018

  15. [15]

    Object-Centric Neural Scene Rendering

    Michelle Guo, Alireza Fathi, Jiajun Wu, and Thomas Funkhouser. Object-Centric Neural Scene Rendering. arXiv preprint arXiv:2012.08503, 2020

    work page arXiv 2012

  16. [16]

    Vmesh: Hybrid volume-mesh representation for efficient view synthesis

    Yuan-Chen Guo, Yan-Pei Cao, Chen Wang, Yu He, Ying Shan, Xiaohu Qie, and Song-Hai Zhang. Vmesh: Hybrid volume-mesh representation for efficient view synthesis. arXiv preprint arXiv:2303.16184, 2023

    work page arXiv 2023

  17. [17]

    Baking neural radiance fields for real-time view synthesis

    Peter Hedman, Pratul P Srinivasan, Ben Mildenhall, Jonathan T Barron, and Paul Debevec. Baking neural radiance fields for real-time view synthesis. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5875–5884, 2021

    2021

  18. [18]

    Hoetzlein

    Rama C. Hoetzlein. Fast fixed-radius nearest neighbors: Interactive million-particle fluids, 2014. GPU Technology Conference

    2014

  19. [19]

    Kinectfusion: real-time 3D reconstruction and interaction using a moving depth camera

    Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux, Richard Newcombe, Pushmeet Kohli, Jamie Shotton, Steve Hodges, Dustin Freeman, Andrew Davi- son, et al. Kinectfusion: real-time 3D reconstruction and interaction using a moving depth camera. InProceedings of the 24th annual ACM symposium on User interface software and technology, pages 559–568, 2011

    2011

  20. [20]

    Large Scale Multi-view Stereopsis Evaluation

    Rasmus Jensen, Anders Dahl, George Vogiatzis, Engil Tola, and Henrik Aanæs. Large Scale Multi-view Stereopsis Evaluation. In2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 406–413. IEEE, 2014

    2014

  21. [21]

    CoNeRF: Controllable Neural Radiance Fields

    Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzci´nski, and Andrea Tagliasacchi. CoNeRF: Controllable Neural Radiance Fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18623–18632, 2022

    2022

  22. [22]

    Forsyth, and Derek Hoiem

    Kevin Karsch, Varsha Hedau, David A. Forsyth, and Derek Hoiem. Rendering Synthetic Objects into Legacy Pho- tographs.ACM Trans. Graph., 30(6):157, 2011

    2011

  23. [23]

    Kazhdan, Matthew Bolitho, and Hugues Hoppe

    Michael M. Kazhdan, Matthew Bolitho, and Hugues Hoppe. Poisson Surface Reconstruction. InProceedings of Eurographics Symposium on Geometry Processing, pages 61– 70, 2006

    2006

  24. [24]

    3d gaussian splatting for real-time radiance field rendering.ACM Transactions on Graphics (ToG), 42(4):1–14, 2023

    Bernhard Kerbl, Georgios Kopanas, Thomas Leimk ¨uhler, and George Drettakis. 3d gaussian splatting for real-time radiance field rendering.ACM Transactions on Graphics (ToG), 42(4):1–14, 2023

    2023

  25. [25]

    Lerf: Language em- bedded radiance fields

    Justin Kerr, Chung Min Kim, Ken Goldberg, Angjoo Kanazawa, and Matthew Tancik. Lerf: Language em- bedded radiance fields. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 19729– 19739, 2023

    2023

  26. [26]

    3D Object Manipulation in a Single Photograph JOURNAL OF LATEX CLASS FILES, VOL

    Natasha Kholgade, Tomas Simon, Alexei Efros, and Yaser Sheikh. 3D Object Manipulation in a Single Photograph JOURNAL OF LATEX CLASS FILES, VOL. 18, NO. 9, SEPTEMBER 2020 16 Using Stock 3D Models.ACM Transactions on Graphics (TOG), 33(4):1–12, 2014

    2020

  27. [27]

    Garfield: Group anything with radiance fields

    Chung Min Kim, Mingxuan Wu, Justin Kerr, Ken Gold- berg, Matthew Tancik, and Angjoo Kanazawa. Garfield: Group anything with radiance fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21530–21539, 2024

    2024

  28. [28]

    Segment Anything

    Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer White- head, Alexander C Berg, Wan-Yen Lo, et al. Segment anything.arXiv preprint arXiv:2304.02643, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  29. [29]

    Decomposing nerf for editing via feature field dis- tillation.Advances in Neural Information Processing Systems, 35:23311–23330, 2022

    Sosuke Kobayashi, Eiichi Matsumoto, and Vincent Sitz- mann. Decomposing nerf for editing via feature field dis- tillation.Advances in Neural Information Processing Systems, 35:23311–23330, 2022

    2022

  30. [30]

    Adanerf: Adaptive sampling for real-time rendering of neural radiance fields

    Andreas Kurz, Thomas Neff, Zhaoyang Lv, Michael Zollh¨ofer, and Markus Steinberger. Adanerf: Adaptive sampling for real-time rendering of neural radiance fields. InEuropean Conference on Computer Vision, pages 254–270. Springer, 2022

    2022

  31. [31]

    Nerfacc: Efficient sampling accelerates nerfs

    Ruilong Li, Hang Gao, Matthew Tancik, and Angjoo Kanazawa. Nerfacc: Efficient sampling accelerates nerfs. arXiv preprint arXiv:2305.04966, 2023

    work page arXiv 2023

  32. [32]

    Neuralangelo: High-fidelity neural surface reconstruction

    Zhaoshuo Li, Thomas M ¨uller, Alex Evans, Russell H Tay- lor, Mathias Unberath, Ming-Yu Liu, and Chen-Hsuan Lin. Neuralangelo: High-fidelity neural surface reconstruction. InProceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition, pages 8456–8465, 2023

    2023

  33. [33]

    Stylerf: Zero-shot 3d style transfer of neural radiance fields

    Kunhao Liu, Fangneng Zhan, Yiwen Chen, Jiahui Zhang, Yingchen Yu, Abdulmotaleb El Saddik, Shijian Lu, and Eric P Xing. Stylerf: Zero-shot 3d style transfer of neural radiance fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8338–8348, 2023

    2023

  34. [34]

    Neural Sparse Voxel Fields.Advances in Neural Information Processing Systems, 33:15651–15663, 2020

    Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. Neural Sparse Voxel Fields.Advances in Neural Information Processing Systems, 33:15651–15663, 2020

    2020

  35. [35]

    Neu- ral Actor: Neural Free-view Synthesis of Human Actors with Pose Control.ACM Transactions on Graphics (TOG), 40(6):1–16, 2021

    Lingjie Liu, Marc Habermann, Viktor Rudnev, Kri- pasindhu Sarkar, Jiatao Gu, and Christian Theobalt. Neu- ral Actor: Neural Free-view Synthesis of Human Actors with Pose Control.ACM Transactions on Graphics (TOG), 40(6):1–16, 2021

    2021

  36. [36]

    Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning.The IEEE International Conference on Computer Vision (ICCV), Oct 2019

    Shichen Liu, Tianye Li, Weikai Chen, and Hao Li. Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning.The IEEE International Conference on Computer Vision (ICCV), Oct 2019

    2019

  37. [37]

    Editing Con- ditional Radiance Fields

    Steven Liu, Xiuming Zhang, Zhoutong Zhang, Richard Zhang, Jun-Yan Zhu, and Bryan Russell. Editing Con- ditional Radiance Fields. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5773– 5783, 2021

    2021

  38. [38]

    Marching Cubes: A High Resolution 3D Surface Construction Algorithm

    William E Lorensen and Harvey E Cline. Marching Cubes: A High Resolution 3D Surface Construction Algorithm. ACM SIGGRAPH Computer Graphics, 21(4):163–169, 1987

    1987

  39. [39]

    NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decompo- sition in Indoor Scenes.IEEE Transactions on Visualization and Computer Graphics, 26(12):3434–3445, 2020

    Jundan Luo, Zhaoyang Huang, Yijin Li, Xiaowei Zhou, Guofeng Zhang, and Hujun Bao. NIID-Net: Adapting Surface Normal Knowledge for Intrinsic Image Decompo- sition in Indoor Scenes.IEEE Transactions on Visualization and Computer Graphics, 26(12):3434–3445, 2020

    2020

  40. [40]

    NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

    Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. InEuropean Conference on Computer Vision, pages 405–421. Springer, 2020

    2020

  41. [41]

    Instant Neural Graphics Primitives with a Multiresolution Hash Encoding.ACM Trans

    Thomas M ¨uller, Alex Evans, Christoph Schied, and Alexander Keller. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding.ACM Trans. Graph., 41(4):102:1–102:15, July 2022

    2022

  42. [42]

    Atlas: End-to-End 3D Scene Reconstruction from Posed Images

    Zak Murez, Tarrence van As, James Bartolozzi, Ayan Sinha, Vijay Badrinarayanan, and Andrew Rabinovich. Atlas: End-to-End 3D Scene Reconstruction from Posed Images. InEuropean Conference on Computer Vision, pages 414–431. Springer, 2020

    2020

  43. [43]

    Donerf: Towards real-time rendering of compact neural radiance fields us- ing depth oracle networks

    Thomas Neff, Pascal Stadlbauer, Mathias Parger, Andreas Kurz, Joerg H Mueller, Chakravarty R Alla Chaitanya, An- ton Kaplanyan, and Markus Steinberger. Donerf: Towards real-time rendering of compact neural radiance fields us- ing depth oracle networks. InComputer Graphics Forum, volume 40, pages 45–59. Wiley Online Library, 2021

    2021

  44. [44]

    Giraffe: Repre- senting Scenes as Compositional Generative Neural Fea- ture Fields

    Michael Niemeyer and Andreas Geiger. Giraffe: Repre- senting Scenes as Compositional Generative Neural Fea- ture Fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11453– 11464, 2021

    2021

  45. [45]

    Texture Fields: Learn- ing Texture Representations in Function Space

    Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, and Andreas Geiger. Texture Fields: Learn- ing Texture Representations in Function Space. InProceed- ings of the IEEE/CVF International Conference on Computer Vision, pages 4531–4540, 2019

    2019

  46. [46]

    UNISURF: Unifying Neural Implicit Surfaces and Radi- ance Fields for Multi-View Reconstruction

    Michael Oechsle, Songyou Peng, and Andreas Geiger. UNISURF: Unifying Neural Implicit Surfaces and Radi- ance Fields for Multi-View Reconstruction. InInternational Conference on Computer Vision (ICCV), 2021

    2021

  47. [47]

    Neural Point Light Fields.arXiv preprint arXiv:2112.01473, 2021

    Julian Ost, Issam Laradji, Alejandro Newell, Yuval Bahat, and Felix Heide. Neural Point Light Fields.arXiv preprint arXiv:2112.01473, 2021

    work page arXiv 2021

  48. [48]

    Lo- cally stylized neural radiance fields

    Hong-Wing Pang, Binh-Son Hua, and Sai-Kit Yeung. Lo- cally stylized neural radiance fields. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 307–316, 2023

    2023

  49. [49]

    Nerfies: Deformable Neural Radiance Fields

    Keunhong Park, Utkarsh Sinha, Jonathan T Barron, Sofien Bouaziz, Dan B Goldman, Steven M Seitz, and Ricardo Martin-Brualla. Nerfies: Deformable Neural Radiance Fields. InProceedings of the IEEE/CVF International Con- ference on Computer Vision, pages 5865–5874, 2021

    2021

  50. [50]

    Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, and Steven M

    Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, and Steven M. Seitz. HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields.ACM Trans. Graph., 40(6), dec 2021

    2021

  51. [51]

    Neural body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

    Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, and Xiaowei Zhou. Neural body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9054–9063, 2021

    2021

  52. [52]

    Pois- son Image Editing.ACM Trans

    Patrick P ´erez, Michel Gangnet, and Andrew Blake. Pois- son Image Editing.ACM Trans. Graph., 22(3):313–318, 2003

    2003

  53. [53]

    Nerfmeshing: Distilling neural radiance fields into geometrically-accurate 3d meshes.arXiv preprint arXiv:2303.09431, 2023

    Marie-Julie Rakotosaona, Fabian Manhardt, Diego Martin Arroyo, Michael Niemeyer, Abhijit Kundu, and Federico Tombari. Nerfmeshing: Distilling neural radiance fields into geometrically-accurate 3d meshes.arXiv preprint arXiv:2303.09431, 2023

    work page arXiv 2023

  54. [54]

    KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

    Christian Reiser, Songyou Peng, Yiyi Liao, and An- dreas Geiger. KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 14335–14345, 2021

    2021

  55. [55]

    Neural Voxel Renderer: Learning an Accurate and Controllable Render- ing Tool

    Konstantinos Rematas and Vittorio Ferrari. Neural Voxel Renderer: Learning an Accurate and Controllable Render- ing Tool. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5417–5427, 2020

    2020

  56. [56]

    Free View Synthesis

    Gernot Riegler and Vladlen Koltun. Free View Synthesis. InEuropean Conference on Computer Vision, pages 623–640. Springer, 2020

    2020

  57. [57]

    Stable View Synthe- sis

    Gernot Riegler and Vladlen Koltun. Stable View Synthe- sis. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12216–12225, 2021

    2021

  58. [58]

    Sara Fridovich-Keil and Alex Yu, Matthew Tancik, Qin- JOURNAL OF LATEX CLASS FILES, VOL. 18, NO. 9, SEPTEMBER 2020 17 hong Chen, Benjamin Recht, and Angjoo Kanazawa. Plenoxels: Radiance Fields without Neural Networks. In CVPR, 2022

    2020

  59. [59]

    Sch ¨onberger and Jan-Michael Frahm

    Johannes L. Sch ¨onberger and Jan-Michael Frahm. Structure-from-Motion Revisited. InProceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages 4104–4113. IEEE Computer Society, 2016

    2016

  60. [60]

    GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis.Advances in Neural Information Processing Systems, 33:20154–20166, 2020

    Katja Schwarz, Yiyi Liao, Michael Niemeyer, and Andreas Geiger. GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis.Advances in Neural Information Processing Systems, 33:20154–20166, 2020

    2020

  61. [61]

    Ad- versarial Scene Editing: Automatic Object Removal from Weak Supervision.Advances in Neural Information Process- ing Systems, 31, 2018

    Rakshith R Shetty, Mario Fritz, and Bernt Schiele. Ad- versarial Scene Editing: Automatic Object Removal from Weak Supervision.Advances in Neural Information Process- ing Systems, 31, 2018

    2018

  62. [62]

    Very Deep Convolutional Networks for Large-Scale Image Recognition

    Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  63. [63]

    As-rigid-as-possible Surface Modeling

    Olga Sorkine and Marc Alexa. As-rigid-as-possible Surface Modeling. InSymposium on Geometry Processing, volume 4, pages 109–116, 2007

    2007

  64. [64]

    NeRV: Neural Reflectance and Visibility Fields for Relight- ing and View Synthesis

    Pratul P Srinivasan, Boyang Deng, Xiuming Zhang, Matthew Tancik, Ben Mildenhall, and Jonathan T Barron. NeRV: Neural Reflectance and Visibility Fields for Relight- ing and View Synthesis. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7495–7504, 2021

    2021

  65. [65]

    Direct voxel grid optimization: Super-fast convergence for radi- ance fields reconstruction

    Cheng Sun, Min Sun, and Hwann-Tzong Chen. Direct voxel grid optimization: Super-fast convergence for radi- ance fields reconstruction. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5459–5469, 2022

    2022

  66. [66]

    FENeRF: Face Editing in Neural Radiance Fields

    Jingxiang Sun, Xuan Wang, Yong Zhang, Xiaoyu Li, Qi Zhang, Yebin Liu, and Jue Wang. FENeRF: Face Editing in Neural Radiance Fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7672–7682, 2022

    2022

  67. [67]

    NeuralRecon: Real-time Coherent 3D Reconstruction from Monocular Video

    Jiaming Sun, Yiming Xie, Linghao Chen, Xiaowei Zhou, and Hujun Bao. NeuralRecon: Real-time Coherent 3D Reconstruction from Monocular Video. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15598–15607, 2021

    2021

  68. [68]

    Block-NeRF: Scalable Large Scene Neural View Synthesis

    Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul P Srinivasan, Jonathan T Barron, and Henrik Kretzschmar. Block-NeRF: Scalable Large Scene Neural View Synthesis. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8248–8258, 2022

    2022

  69. [69]

    Delicate textured mesh recovery from nerf via adaptive surface refinement.arXiv preprint arXiv:2303.02091, 2023

    Jiaxiang Tang, Hang Zhou, Xiaokang Chen, Tianshu Hu, Errui Ding, Jingdong Wang, and Gang Zeng. Delicate textured mesh recovery from nerf via adaptive surface refinement.arXiv preprint arXiv:2303.02091, 2023

    work page arXiv 2023

  70. [70]

    De- ferred Neural Rendering: Image Synthesis Using Neural Textures.ACM Transactions on Graphics (TOG), 38(4):1–12, 2019

    Justus Thies, Michael Zollh ¨ofer, and Matthias Nießner. De- ferred Neural Rendering: Image Synthesis Using Neural Textures.ACM Transactions on Graphics (TOG), 38(4):1–12, 2019

    2019

  71. [71]

    Least-Squares Estimation of Transforma- tion Parameters Between Two Point Patterns.IEEE Transac- tions on Pattern Analysis & Machine Intelligence, 13(04):376– 380, 1991

    Shinji Umeyama. Least-Squares Estimation of Transforma- tion Parameters Between Two Point Patterns.IEEE Transac- tions on Pattern Analysis & Machine Intelligence, 13(04):376– 380, 1991

    1991

  72. [72]

    Let there be color! Large-Scale Texturing of 3D Reconstruc- tions

    Michael Waechter, Nils Moehrle, and Michael Goesele. Let there be color! Large-Scale Texturing of 3D Reconstruc- tions. InEuropean Conference on Computer Vision, pages 836–850. Springer, 2014

    2014

  73. [73]

    Clip-nerf: Text-and-image driven manip- ulation of neural radiance fields

    Can Wang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. Clip-nerf: Text-and-image driven manip- ulation of neural radiance fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, pages 3835–3844, 2022

    2022

  74. [74]

    NeuS: Learning Neu- ral Implicit Surfaces by Volume Rendering for Multi-view Reconstruction.NeurIPS, 2021

    Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. NeuS: Learning Neu- ral Implicit Surfaces by Volume Rendering for Multi-view Reconstruction.NeurIPS, 2021

    2021

  75. [75]

    IBRNet: Learning Multi-view Image-based Rendering

    Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P Srinivasan, Howard Zhou, Jonathan T Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. IBRNet: Learning Multi-view Image-based Rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4690–4699, 2021

    2021

  76. [76]

    Unsupervised Texture Transfer from Images to Model Collections.ACM Trans

    Tuanfeng Y Wang, Hao Su, Qixing Huang, Jingwei Huang, Leonidas J Guibas, and Niloy J Mitra. Unsupervised Texture Transfer from Images to Model Collections.ACM Trans. Graph., 35(6):177–1, 2016

    2016

  77. [77]

    SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

    Weiyue Wang, Ronald Yu, Qiangui Huang, and Ulrich Neumann. SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2569–2578, 2018

    2018

  78. [78]

    Neumanifold: Neural watertight manifold reconstruction with efficient and high-quality rendering support.arXiv preprint arXiv:2305.17134, 2023

    Xinyue Wei, Fanbo Xiang, Sai Bi, Anpei Chen, Kalyan Sunkavalli, Zexiang Xu, and Hao Su. Neumanifold: Neural watertight manifold reconstruction with efficient and high-quality rendering support.arXiv preprint arXiv:2305.17134, 2023

    work page arXiv 2023

  79. [79]

    NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

    Fanbo Xiang, Zexiang Xu, Milos Hasan, Yannick Hold- Geoffroy, Kalyan Sunkavalli, and Hao Su. NeuTex: Neural Texture Mapping for Volumetric Neural Rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7119–7128, 2021

    2021

  80. [80]

    CityNeRF: Building NeRF at City Scale.arXiv preprint arXiv:2112.05504, 2021

    Yuanbo Xiangli, Linning Xu, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, Bo Dai, and Dahua Lin. CityNeRF: Building NeRF at City Scale.arXiv preprint arXiv:2112.05504, 2021

    work page arXiv 2021

Showing first 80 references.