REVIEW 4 major objections 4 minor 53 references
FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency
T0 review · 4 major / 4 minor · reviewed 2026-08-10 · deepseek-v4-flash
Pith's one-line read FatesGS claims that sparse-view reconstruction can be made more accurate and 60 to 200 times faster by adding patch-wise depth ranking and smoothing plus multi-view feature alignment to 2D Gaussian splatting.
desk verdict Solid engineering paper: 14-minute sparse-view reconstruction with accuracy on par with NeuSurf's 14-hour method, but the evaluation needs error bars and the pretrained-feature circularity should be acknowledged. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The load-bearing object is the 2D Gaussian primitive — a flat ellipse with learnable center, scale, rotation, opacity, and color, rendered by depth-sorted $\alpha$ blending as in the 2DGS backbone, so that rendered depth comes from ray-splat intersection. Around that backbone the paper places three loss terms that carry the argument. The patch ranking loss ($L_r$, Eq. 8) shuffles pixels within $M \times M$ patches and penalizes rendered-depth pairs whose order disagrees with monocular depth order, transferring relative scale without committing to absolute scale. The smoothness loss ($L_s$, Eq. 9) penalizes rendered-depth jumps between adjacent pixels while threshold margins protect real boundaries. The multi-view feature loss ($L_f$, Eq. 14) unprojects each pixel's rendered depth into 3D, reprojects the point into source views, and aligns multi-resolution features from a frozen feature network by cosine similarity, weighted by a visibility indicator (Eq. 15) that keeps only the nearest reprojected point per ray. The full objective is $L = L_c + \lambda_1 L_r + \lambda_2 L_s + \lambda_3 L_f + \lambda_4 L_d + \lambda_5 L_n$, with the backbone's depth-distortion and normal-consistency terms retained.
What would settle it
Two concrete checks would settle the central claim. First, initialize the Gaussians from a deliberately corrupted point cloud (translated or scaled away from the true surface) on a DTU three-view scene and measure the resulting Chamfer Distance: recovery would show the consistency losses genuinely guide geometry, while a large CD jump would show the accuracy depends on COLMAP's initialization rather than the proposed mechanism. Second, replace the frozen feature extractor (Vis-MVSNet) with a different pretrained network and re-run the DTU large-overlap benchmark: a substantial change in mean CD would show the reported 0.92 is carried by the specific feature network's invariance rather than by the consistency formulation itself.
Extended reading notes
Core claim
The central claim, stated on the paper's own terms, is that the geometric collapse of Gaussian splatting under sparse views is not an inherent limitation of the representation but a correctable failure of optimization, and that two complementary consistency priors suffice to correct it without large-scale pretraining. Intra-view depth consistency — enforcing that rendered depths inside local patches respect the same ranking as a monocular depth estimate, together with a smoothness loss between adjacent pixels — stabilizes the coarse global shape and suppresses the floaters that arise from overfitting a handful of training views. Multi-view feature alignment then recovers detail: each depth-rendered pixel is unprojected into 3D, reprojected into the other views, and its multi-resolution features (from a frozen feature network) are aligned by cosine similarity under an occlusion mask computed from the rendered depth itself. The paper reports that this combination attains a mean Chamfer Distance of 0.92 on the DTU large-overlap three-view benchmark, the best among all compared methods, while training in about 14 minutes per scene, and that the same hyperparameters transfer to BlendedMVS and to the harder little-overlap setting without re-tuning.
Load-bearing premise
The load-bearing premise is that the occlusion mask used by the multi-view feature loss — computed from the very rendered depth being optimized — stays accurate enough during early training that feature correspondences are not dominated by occluded or misprojected pixels; if the initial Gaussians are poorly localized under sparse views, the depth-visibility-feature loop can lock onto wrong geometry, and the frozen feature network must also remain reliable on the target scene.
Editorial extensions
If this is right
- Sparse-view accuracy and speed stop being a trade-off: the reported DTU three-view mean Chamfer Distance of 0.92 beats every method compared while per-scene training drops to about 14 minutes on a single RTX 3090 using 4 GB of memory.
- The 60x to 200x training speedup relative to per-scene optimizers such as NeuSurf and to pretrained generalizers such as UFORecon would let reconstruction run in interactive or on-site loops instead of as a scheduled job.
- Because the identical hyperparameters are reported on DTU large-overlap, DTU little-overlap, and BlendedMVS, the constraints are not tuned to a single benchmark, which the paper offers as evidence of generalization.
- Reconstruction quality scales smoothly with view count (reported mean CD 0.92 at 3 views, 0.85 at 6, 0.79 at 9, 0.61 with all views), so the method degrades gracefully as views are removed rather than collapsing.
- The same pipeline improves few-shot novel view synthesis as a byproduct (reported PSNR 21.80, SSIM 0.904, LPIPS 0.077 on DTU with three input views), coupling geometry and rendering quality in one optimization.
Reading between the lines
- A stress test the paper does not run: initialize the Gaussians from deliberately wrong or perturbed point clouds (translated, scaled, or partially missing). If the feature alignment loss redirects the geometry to the true surface, the depth-visibility recursion is robust; if it locks onto floaters, the method inherits the initialization's failure mode and the 0.92 result depends on COLMAP's initia
- The recipe generalizes as a template for under-constrained 3D fitting generally: a cheap order-only signal (rankings) stabilizes coarse shape without scale commitment, and a frozen feature metric fixes absolute position. Porting the same two-stage design into NeRF-based or SDF-based sparse-view pipelines is a direct and testable extension.
- The accuracy ceiling is set by the frozen feature extractor's invariance: on scenes whose texture statistics differ from multi-view-stereo training data, such as reflective, transparent, or heavily textureless surfaces, the feature loss may silently misalign with no learned recourse. A domain-transfer experiment swapping the feature network would quantify how much of the reported Chamfer distance
- With 14-minute training and 4 GB peak memory, the method sits at the threshold of laptop-GPU and on-device scanning; the paper notes the efficiency but does not explore that application, which is where the practical impact would be largest.
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper proposes FatesGS, a per-scene optimization method for sparse-view surface reconstruction built on 2D Gaussian Splatting. The method adds three ingredients to a 2DGS backbone: a patch-wise depth ranking loss using monocular depth, a depth smoothing loss, and a multi-view feature alignment loss that compares frozen Vis-MVSNet features of reprojected surface points under a rendered-depth visibility mask. The authors report a mean Chamfer Distance of 0.92 on the DTU large-overlap three-view setting, a training time of about 14 minutes per scene, and additional experiments on the little-overlap setting, dense-view reconstruction, depth prediction, and novel view synthesis. Ablation studies attribute most of the accuracy gain to the multi-view feature loss.
Significance. If the empirical claims hold, FatesGS is a practically useful contribution: it achieves the best mean Chamfer Distance among the compared methods on the DTU large-overlap sparse-view benchmark while reducing per-scene optimization time by roughly an order of magnitude relative to NeuSurf, and it avoids dataset-scale pretraining. The paper is strong in experimental breadth: it provides comparisons with MVS, generalizable implicit, per-scene implicit, and Gaussian-splatting baselines, along with ablations, depth evaluation, and additional qualitative results. The main weaknesses are statistical: no error bars or significance tests are reported, and the claimed superiority is not uniform across settings or scans. The central feature loss also relies on a hard visibility mask computed from the depth being optimized, and the paper does not analyze the failure modes of this self-referential mechanism. These issues affect the load-bearing accuracy claim and need to be addressed before the paper can be accepted.
major comments (4)
- [Multi-View Feature Alignment, Eq. (15)] The visibility mask v_{r,s,i} in Eq. (15) is a hard Iverson bracket computed from the rendered depth that is itself the optimization target. Because Table 8 shows that the visibility item is important (removing v degrades mean CD from 1.37 to 1.62) and Table 4 shows that Lf is the main contributor to accuracy (without Lf, CD rises from 1.37 to 2.47), early incorrect depth can systematically mask the correct correspondences and lock the geometry into a local minimum. The current ablations only remove the whole loss or the whole mask; they do not measure mask accuracy, masked-pixel statistics, or sensitivity to the COLMAP initialization. Please add diagnostics that track mask errors over training and test a softened visibility formulation or a coarse-to-fine depth schedule to verify that the reported gains are not an artifact of this chicken-and-egg loop.
- [Experiments, Table 1 and Supplementary Table 2] The empirical claims are not supported with statistical evidence. No error bars, standard deviations, or significance tests are reported for the mean Chamfer Distance values. On the large-overlap setting, FatesGS is worse than NeuSurf on at least four of fifteen scans (scans 55, 63, 69, and 114), and on the little-overlap setting in Supplementary Table 2 the mean CD is 1.37 versus NeuSurf's 1.35, so FatesGS is not state of the art in that setting. The statements in the abstract and conclusion that the method 'outperforms' prior methods in two distinct settings should be qualified, and a paired test or per-scan breakdown should be reported to establish whether the large-overlap mean improvement is significant.
- [Experimental Settings, Implementation Details; BlendedMVS results] The evaluation protocol contains a circularity risk: the frozen feature extractor fϕ is Vis-MVSNet, which is trained on DTU, and the loss weights and margins appear to be tuned on the same DTU scans used for evaluation. The BlendedMVS generalization experiment is only qualitative (Figure 3) and reports no Chamfer Distance numbers, so it does not quantitatively establish cross-dataset robustness. Please report quantitative BlendedMVS results, and ideally include an ablation that replaces Vis-MVSNet with a feature network not trained on DTU, to show that the feature-consistency loss transfers outside the training distribution.
- [Efficiency, Table 2] The claimed 60x to 200x speedup conflates different training protocols. Table 2 compares the proposed per-scene optimization time (14 minutes) with the pre-training time of generalizable methods such as UFORecon (about 10 days), but for those methods pre-training is amortized and the per-scene inference cost is what matters. Without reporting per-scene inference times for the generalizable baselines, the speedup claim is overstated. The paper should state explicitly whether the speedup refers to per-scene optimization only, and should report the per-scene inference or fine-tuning times of the compared methods, or remove the comparison with pre-training time from the headline claim.
minor comments (4)
- [Loss Functions, Eq. (18)] The normal consistency loss definition is unclear: the text says both n_i^T and N are 'estimated normal near the depth point'. Please clarify which normal is the Gaussian primitive normal and which is the rendered-surface normal, and check the formula against the 2DGS formulation.
- [Ablation Study, Table 4] The result that Lr and Ls alone (mean CD 2.56) are worse than the baseline without any of the three losses (2.47) is counterintuitive and deserves a more mechanistic explanation than the statement that the contributions are 'neither isolated nor merely additive'. Consider reporting an interaction analysis or per-scan results for this ablation.
- [Supplementary Material, Section B] There are several typos, including 'little-overlap seltting' in the supplementary text and the title 'F atesGS', and the duplicated definition of the Sun et al. reference (2024a and 2024b appear to cite the same paper). These should be corrected.
- [Figure 2] The overview figure is difficult to read: the loss labels λ1 through λ5 and the feature-level symbols are too small, and the flow of the multi-view feature alignment path is not clear. Please enlarge the fonts and annotate the modules that correspond to Eqs. (8), (9), and (14).
Circularity Check
No equation-level circularity; the SOTA claim is an empirical benchmark result. The only same-author citation is a non-load-bearing evaluation-protocol reference, and the DTU-pretrained feature net is a validity caveat, not a circular reduction.
full rationale
Walking the derivation chain, the surface is obtained by optimizing the combined loss in Eq. 16: color reproduction (Eq. 17), depth-distortion and normal-consistency regularizers (Eq. 18), patch-wise monocular-depth ranking (Eq. 8), smoothness (Eq. 9), and multi-view feature alignment (Eq. 14). Each term compares rendered quantities to signals that are either measured pixels, an external frozen depth prior (Marigold), an external frozen feature network (Vis-MVSNet), or geometric consistency terms. None of these terms is defined in terms of the reported Chamfer Distance or the extracted mesh, so the accuracy claim is an empirical outcome, not a tautology. The visibility mask in Eq. 15 is computed from the very rendered depth being optimized, but it is an iterative nearest-point occlusion test rather than an identity: the loss still carries external feature information and does not vanish by construction. The risk that early misprojections lock geometry into a local minimum is a robustness concern, not derivational circularity. The only same-author citation, NeuSurf (Huang et al. 2024b), is used for the evaluation protocol and as a baseline; it is not a load-bearing premise for any equation or for the reported CD. The DTU evaluation does carry a domain-overlap caveat because the frozen feature extractor is an MVS network trained on MVS data including DTU, and hyperparameters are not chosen on a separate validation split; these affect external validity and should be disclosed, but they do not make the prediction equivalent to its input by construction. Overall, no significant circularity is present; the score of 2 reflects the minor non-load-bearing self-citation and benchmark caveats, not a circular derivation.
Assumptions & free parameters
free parameters (4)
- loss weights λ1, λ2, λ3, λ4, λ5 =
10, 1, 1.5, 10^4, 0.05
- margins m, m_e, m_t =
1e-4, 1e-2, 1e-4
- patch size M =
not stated
- feature levels =
l = 1, 2
assumptions (5)
- standard math 2D Gaussian splatting rendering equations from 2DGS provide surface-aligned geometry
- domain assumption Monocular depth from Marigold provides reliable relative depth ordering within local patches
- domain assumption Vis-MVSNet features are viewpoint-invariant enough for multi-view matching on target scenes
- domain assumption Camera poses are known
- domain assumption COLMAP initialization provides a point cloud adequate for Gaussian insertion
Cite this review
Pith. "Pith review of FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency." pith.science (2026). https://pith.science/paper/WUDGNM4J
@misc{pith2026250104628,
author = {Pith},
title = {Pith review of: FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency},
year = {2026},
howpublished = {\url{https://pith.science/paper/WUDGNM4J}},
note = {Machine review of arXiv:2501.04628}
}
read the original abstract
Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed surface reconstruction while ensuring fast training speed. However, these methods still require dense input views, and their output quality significantly degrades with sparse views. We observed that the Gaussian primitives tend to overfit the few training views, leading to noisy floaters and incomplete reconstruction surfaces. In this paper, we present an innovative sparse-view reconstruction framework that leverages intra-view depth and multi-view feature consistency to achieve remarkably accurate surface reconstruction. Specifically, we utilize monocular depth ranking information to supervise the consistency of depth distribution within patches and employ a smoothness loss to enhance the continuity of the distribution. To achieve finer surface reconstruction, we optimize the absolute position of depth through multi-view projection features. Extensive experiments on DTU and BlendedMVS demonstrate that our method outperforms state-of-the-art methods with a speedup of 60x to 200x, achieving swift and fine-grained mesh reconstruction without the need for costly pre-training.
Figures
Figures from the paper (4 more)
Reference graph
Works this paper leans on
-
[1]
Chen, H.; Li, C.; and Lee, G. H. 2023. Neusg: Neural implicit surface reconstruction with 3d gaussian splatting guidance. arXiv preprint arXiv:2312.00846
arXiv 2023
-
[2]
Chen, H.; Wei, F.; Li, C.; Huang, T.; Wang, Y.; and Lee, G. H. 2024. VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction. arXiv preprint arXiv:2406.05774
arXiv 2024
-
[3]
Choe, J.; Im, S.; Rameau, F.; Kang, M.; and Kweon, I.-S. 2021. VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 16066--16075
work page 2021
-
[4]
Chung, J.; Oh, J.; and Lee, K. M. 2023. Depth-regularized optimization for 3d gaussian splatting in few-shot images. arXiv preprint arXiv:2311.13398
arXiv 2023
-
[5]
Dai, P.; Xu, J.; Xie, W.; Liu, X.; Wang, H.; and Xu, W. 2024. High-quality Surface Reconstruction using Gaussian Surfels. In SIGGRAPH 2024 Conference Papers. Association for Computing Machinery
work page 2024
-
[6]
Darmon, F.; Bascle, B.; Devaux, J.-C.; Monasse, P.; and Aubry, M. 2022. Improving neural implicit surfaces geometry with patch warping. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6260--6269
work page 2022
-
[7]
Ding, Y.; Yuan, W.; Zhu, Q.; Zhang, H.; Liu, X.; Wang, Y.; and Liu, X. 2022. Transmvsnet: Global context-aware multi-view stereo network with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8585--8594
work page 2022
-
[8]
Fu, Q.; Xu, Q.; Ong, Y. S.; and Tao, W. 2022. Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction. In Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; and Oh, A., eds., Advances in Neural Information Processing Systems, volume 35, 3403--3416. Curran Associates, Inc
work page 2022
Show all 53 references
-
[9]
Furukawa, Y.; and Ponce, J. 2010. Accurate, Dense, and Robust Multiview Stereopsis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(8): 1362--1376
2010
-
[10]
Galliani, S.; Lasinger, K.; and Schindler, K. 2015. Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. In 2015 IEEE International Conference on Computer Vision (ICCV), 873--881
2015
-
[11]
Gu \'e don, A.; and Lepetit, V. 2023. Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering. arXiv preprint arXiv:2311.12775
2023 arXiv
-
[12]
Han, L.; Zhou, J.; Liu, Y.-S.; and Han, Z. 2024. Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis. In Advances in Neural Information Processing Systems (NeurIPS)
2024
-
[13]
Huang, B.; Yu, Z.; Chen, A.; Geiger, A.; and Gao, S. 2024 a . 2D Gaussian Splatting for Geometrically Accurate Radiance Fields. In SIGGRAPH 2024 Conference Papers. Association for Computing Machinery
2024
-
[14]
Huang, H.; Wu, Y.; Zhou, J.; Gao, G.; Gu, M.; and Liu, Y.-S. 2024 b . NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, 2312--2320
2024
-
[15]
Jensen, R.; Dahl, A.; Vogiatzis, G.; Tola, E.; and Aanæs, H. 2014. Large Scale Multi-view Stereopsis Evaluation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, 406--413
2014
-
[16]
Ji, M.; Gall, J.; Zheng, H.; Liu, Y.; and Fang, L. 2017. SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2307--2315
2017
-
[17]
C.; and Schindler, K
Ke, B.; Obukhov, A.; Huang, S.; Metzger, N.; Daudt, R. C.; and Schindler, K. 2024. Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2024
-
[18]
Kerbl, B.; Kopanas, G.; Leimk \"u hler, T.; and Drettakis, G. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics, 42(4): 1--14
2023
-
[19]
Kostrikov, I.; Horbert, E.; and Leibe, B. 2014. Probabilistic Labeling Cost for High-Accuracy Multi-view Reconstruction. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, 1534--1541
2014
-
[20]
Lhuillier, M.; and Quan, L. 2005. A quasi-dense approach to surface reconstruction from uncalibrated images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(3): 418--433
2005
-
[21]
Li, J.; Zhang, J.; Bai, X.; Zheng, J.; Ning, X.; Zhou, J.; and Gu, L. 2024. Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normalization. arXiv preprint arXiv:2403.06912
2024 arXiv
-
[22]
H.; Unberath, M.; Liu, M.-Y.; and Lin, C.-H
Li, Z.; M \"u ller, T.; Evans, A.; Taylor, R. H.; Unberath, M.; Liu, M.-Y.; and Lin, C.-H. 2023. Neuralangelo: High-fidelity neural surface reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8456--8465
2023
-
[23]
Liang, Y.; He, H.; and Chen, Y. 2024. ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction. Advances in Neural Information Processing Systems, 36
2024
-
[24]
Long, X.; Lin, C.; Wang, P.; Komura, T.; and Wang, W. 2022. Sparseneus: Fast generalizable neural surface reconstruction from sparse views. In European Conference on Computer Vision, 210--227. Springer
2022
-
[25]
Lyu, X.; Sun, Y.-T.; Huang, Y.-H.; Wu, X.; Yang, Z.; Chen, Y.; Pang, J.; and Qi, X. 2024. 3dgsr: Implicit surface reconstruction with 3d gaussian splatting. arXiv preprint arXiv:2404.00409
2024 arXiv
-
[26]
P.; Tancik, M.; Barron, J
Mildenhall, B.; Srinivasan, P. P.; Tancik, M.; Barron, J. T.; Ramamoorthi, R.; and Ng, R. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In Vedaldi, A.; Bischof, H.; Brox, T.; and Frahm, J.-M., eds., Computer Vision -- ECCV 2020, 405--421. Cham: ...
2020
-
[27]
J.; Han, K
Na, Y.; Kim, W. J.; Han, K. B.; Ha, S.; and Yoon, S.-E. 2024. UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets
2024
-
[28]
Peng, R.; Gu, X.; Tang, L.; Shen, S.; Yu, F.; and Wang, R. 2023. GenS: Generalizable Neural Surface Reconstruction from Multi-View Images. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)
2023
-
[29]
Ramon, E.; Triginer, G.; Escur, J.; Pumarola, A.; Garcia, J.; Giro-i Nieto, X.; and Moreno-Noguer, F. 2021. H3d-net: Few-shot high-fidelity 3d head reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 5620--5629
2021
-
[30]
Ren, Y.; Zhang, T.; Pollefeys, M.; S \"u sstrunk, S.; and Wang, F. 2023. Volrecon: Volume rendering of signed ray distance functions for generalizable multi-view reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16685--16695
2023
-
[31]
L.; and Frahm, J.-M
Schonberger, J. L.; and Frahm, J.-M. 2016. Structure-from-motion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4104--4113
2016
-
[32]
L.; Zheng, E.; Frahm, J.-M.; and Pollefeys, M
Sch \"o nberger, J. L.; Zheng, E.; Frahm, J.-M.; and Pollefeys, M. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. In Leibe, B.; Matas, J.; Sebe, N.; and Welling, M., eds., Computer Vision -- ECCV 2016, 501--518. Cham: Springer International Publishing. ISBN...
2016
-
[33]
Somraj, N.; Karanayil, A.; and Soundararajan, R. 2023. Simplenerf: Regularizing sparse input neural radiance fields with simpler solutions. In SIGGRAPH Asia 2023 Conference Papers, 1--11
2023
-
[34]
Somraj, N.; and Soundararajan, R. 2023. Vip-nerf: Visibility prior for sparse input neural radiance fields. In ACM SIGGRAPH 2023 Conference Proceedings, 1--11
2023
-
[36]
Sun, W.; Zhang, Q.; Zhou, Y.; Ye, Q.; Jiao, J.; and Li, Y. 2024 b . Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian. arXiv preprint arXiv:2405.19657
2024 arXiv
-
[37]
Turkulainen, M.; Ren, X.; Melekhov, I.; Seiskari, O.; Rahtu, E.; and Kannala, J. 2024. DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing. arXiv preprint arXiv:2403.17822
2024 arXiv
-
[38]
G.; and Zhang, H
Vora, A.; Patil, A. G.; and Zhang, H. 2023. DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularization. arXiv preprint arXiv:2306.04699
2023 arXiv
-
[39]
C.; and Liu, Z
Wang, G.; Chen, Z.; Loy, C. C.; and Liu, Z. 2023. Sparsenerf: Distilling depth ranking for few-shot novel view synthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 9065--9076
2023
-
[40]
Wang, P.; Liu, L.; Liu, Y.; Theobalt, C.; Komura, T.; and Wang, W. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. Advances in Neural Information Processing Systems, 34: 27171--27183
2021
-
[41]
Xiong, H.; Muttukuru, S.; Upadhyay, R.; Chari, P.; and Kadambi, A. 2023. Sparsegs: Real-time 360 \ deg \ sparse view synthesis using gaussian splatting. arXiv preprint arXiv:2312.00206
2023 arXiv
-
[42]
Xu, L.; Guan, T.; Wang, Y.; Liu, W.; Zeng, Z.; Wang, J.; and Yang, W. 2023. C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstruction. arXiv preprint arXiv:2306.10003
2023 arXiv
-
[43]
Xu, Q.; and Tao, W. 2019. Multi-Scale Geometric Consistency Guided Multi-View Stereo. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2019
-
[44]
Yao, Y.; Luo, Z.; Li, S.; Fang, T.; and Quan, L. 2018. Mvsnet: Depth inference for unstructured multi-view stereo. In Proceedings of the European conference on computer vision (ECCV), 767--783
2018
-
[45]
Yao, Y.; Luo, Z.; Li, S.; Zhang, J.; Ren, Y.; Zhou, L.; Fang, T.; and Quan, L. 2020. BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks. Computer Vision and Pattern Recognition (CVPR)
2020
-
[46]
Yariv, L.; Gu, J.; Kasten, Y.; and Lipman, Y. 2021. Volume rendering of neural implicit surfaces. Advances in Neural Information Processing Systems, 34: 4805--4815
2021
-
[47]
Yu, Z.; Peng, S.; Niemeyer, M.; Sattler, T.; and Geiger, A. 2022. Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction. Advances in neural information processing systems, 35: 25018--25032
2022
-
[48]
S.; Li, K.; Agarwal, H.; and Reid, I
Zhan, H.; Garg, R.; Weerasekera, C. S.; Li, K.; Agarwal, H.; and Reid, I. 2018. Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In Proceedings of the IEEE conference on computer vision and pattern recognition, 340--349
2018
-
[49]
Zhang, J.; Yao, Y.; Li, S.; Luo, Z.; and Fang, T. 2020. Visibility-aware Multi-view Stereo Network. British Machine Vision Conference (BMVC)
2020
-
[50]
Zhang, W.; Liu, Y.-S.; and Han, Z. 2024. Neural signed distance function inference through splatting 3d gaussians pulled on zero-level set. arXiv preprint arXiv:2410.14189
2024 arXiv
-
[51]
Zhu, Z.; Fan, Z.; Jiang, Y.; and Wang, Z. 2023. FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting. arXiv preprint arXiv:2312.00451
2023 arXiv
-
[52]
Zwicker, M.; Pfister, H.; Van Baar, J.; and Gross, M. 2001. EWA volume splatting. In Proceedings Visualization, 2001. VIS'01., 29--538. IEEE
2001
-
[53]
, " * write output.state after.block = add.period write newline
ENTRY address archivePrefix author booktitle chapter edition editor eid eprint howpublished institution isbn journal key month note number organization pages publisher school series title type volume year label extra.label sort.label short.list INTEGERS output.state before.all...
-
[54]
write newline
" write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 gl...
Reviewed August 10, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.