GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
hub Canonical reference
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
Canonical reference. 100% of citing Pith papers cite this work as background.
39
Pith papers citing it
Background
100% of classified citations
abstract
We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for highly complex objects. However, extracting high-quality surfaces from this learned implicit representation is difficult because there are not sufficient surface constraints in the representation. In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation. We observe that the conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision. Experiments on the DTU dataset and the BlendedMVS dataset show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
PAGaS refines multi-view stereo depths by optimizing 1DoF Gaussians whose positions and sizes are fixed by back-projected pixel volumes, producing detailed depth maps that outperform reference baselines on 3D reconstruction benchmarks.
SpUDD defines superpower contours from power diagrams of unsigned distance samples, proves convergence to the true surface, and uses them to generate approximating polygonal meshes that outperform prior strategies.
THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.
SVGS improves Gaussian Splatting novel-view synthesis by replacing single-color primitives with spatially varying color and opacity functions implemented via bilinear interpolation, movable kernels, or tiny neural networks on 2D Gaussian surfels.
A neural-field plus differentiable FEM pipeline recovers spatially varying thermal diffusivity on reconstructed 3D objects from synthetic thermal sequences and partially transfers to held-out heating/cooling conditions.
HSDF-Lane uses a height-aligned signed distance field with differentiable rendering and lane-aware semantic positional encoding to achieve SOTA 3D lane detection and height estimation on OpenLane.
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
Four-stage pipeline reconstructs explicit facial hair strands from multi-view images via 3D Gaussian optimization and curve tracing, claimed as first such method.
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
SAR2Mesh performs coarse-to-fine 3D cardiac mesh reconstruction from SAR radar by template deformation with geometry-aware projection and physics-informed loss, outperforming baselines on the introduced Cardiac Mesh-SAR dataset.
ArtMesh presents a mesh-native pipeline for articulated reconstruction that uses restricted Delaunay remeshing and bidirectional motion consistency to outperform 3D Gaussian Splatting methods on joint estimation and part geometry.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
Sat3R adapts Depth Anything V2 via RPC-aware metric depth fine-tuning to deliver satellite DSM reconstruction with 38% lower MAE than zero-shot baselines and over 300x speedup versus optimization methods.
A new GPU clipping algorithm with directional culling and hierarchical traversal constructs scalable 3D Voronoi and power diagrams for arbitrary point distributions.
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
A greedy algorithm interpolates consistent signed distance functions from discrete samples by treating SDF geometric properties as hard constraints.
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
Anchoring sin/cos-activated latent features on per-primitive virtual scaffolds and decoding them in one deferred MLP pass yields SOTA real-time novel-view synthesis on standard benchmarks.
A pipeline that reconstructs articulated objects from sparse unposed images by aligning independent per-pose reconstructions via learned deformation fields and progressive static/moving part disentanglement.
PREF introduces a phasor volume and tailored Fourier mapping to let shallow MLPs capture high-frequency signals compactly in 2D images, 3D SDFs, and 5D NeRFs.
citing papers explorer
-
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
-
PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement
PAGaS refines multi-view stereo depths by optimizing 1DoF Gaussians whose positions and sizes are fixed by back-projected pixel volumes, producing detailed depth maps that outperform reference baselines on 3D reconstruction benchmarks.
-
SpUDD: Superpower Contouring of Unsigned Distance Data
SpUDD defines superpower contours from power diagrams of unsigned distance samples, proves convergence to the true surface, and uses them to generate approximating polygonal meshes that outperform prior strategies.
-
THOM: Generating Physically Plausible Hand-Object Meshes From Text
THOM is a training-free two-stage framework that generates physically plausible hand-object 3D meshes directly from text by combining text-guided Gaussians with contact-aware physics optimization and VLM refinement.
-
SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
SVGS improves Gaussian Splatting novel-view synthesis by replacing single-color primitives with spatially varying color and opacity functions implemented via bilinear interpolation, movable kernels, or tiny neural networks on 2D Gaussian surfels.
-
Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations
A neural-field plus differentiable FEM pipeline recovers spatially varying thermal diffusivity on reconstructed 3D objects from synthetic thermal sequences and partially transfers to held-out heating/cooling conditions.
-
HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection
HSDF-Lane uses a height-aligned signed distance field with differentiable rendering and lane-aware semantic positional encoding to achieve SOTA 3D lane detection and height estimation on OpenLane.
-
Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
-
Wispy to Voluminous: Prior-free Multi-view Capture of Strand-level Facial Hair
Four-stage pipeline reconstructs explicit facial hair strands from multi-view images via 3D Gaussian optimization and curve tracing, claimed as first such method.
-
Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
-
MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer
MeshFlow uses a contrastive MeshVAE for compact mesh latents and a flow transformer for parallel generation, claiming 18x speedup over autoregressive methods with high accuracy on standard metrics.
-
Towards 3D heart mesh generation using contactless radar imaging and physics-informed neural network
SAR2Mesh performs coarse-to-fine 3D cardiac mesh reconstruction from SAR radar by template deformation with geometry-aware projection and physics-informed loss, outperforming baselines on the introduced Cardiac Mesh-SAR dataset.
-
ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics
ArtMesh presents a mesh-native pipeline for articulated reconstruction that uses restricted Delaunay remeshing and bidirectional motion consistency to outperform 3D Gaussian Splatting methods on joint estimation and part geometry.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
-
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
-
Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning
Sat3R adapts Depth Anything V2 via RPC-aware metric depth fine-tuning to deliver satellite DSM reconstruction with 38% lower MAE than zero-shot baselines and over 300x speedup versus optimization methods.
-
Scalable GPU Construction of 3D Voronoi and Power Diagrams
A new GPU clipping algorithm with directional culling and hierarchical traversal constructs scalable 3D Voronoi and power diagrams for arbitrary point distributions.
-
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
-
Greed for the Spheres: A Signed Distance Interpolation Method
A greedy algorithm interpolates consistent signed distance functions from discrete samples by treating SDF geometric properties as hard constraints.
-
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
-
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Anchoring sin/cos-activated latent features on per-primitive virtual scaffolds and decoding them in one deferred MLP pass yields SOTA real-time novel-view synthesis on standard benchmarks.
-
PAOLI: Pose-free Articulated Object Learning from Sparse-view Images
A pipeline that reconstructs articulated objects from sparse unposed images by aligning independent per-pose reconstructions via learned deformation fields and progressive static/moving part disentanglement.
-
PREF: Phasorial Embedding Fields for Compact Neural Representations
PREF introduces a phasor volume and tailored Fourier mapping to let shallow MLPs capture high-frequency signals compactly in 2D images, 3D SDFs, and 5D NeRFs.
-
VEPHand: View-Efficient Photometric Hand Performance Capture at Scale
End-to-end neural pipeline extracts hand geometry from unmasked limited-view images and registers it to a personalized tetrahedral model via volumetric offsets, achieving SOTA on over 12,000 sequences.
-
GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors
GraspFoM creates a shared 3D latent from SAM3D priors, adds an anchor-initialized diffuser for multimodal grasps, and uses reconstruction-aware scoring plus residual updates to jointly achieve SOTA reconstruction and grasping with few extra parameters.
-
GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images
Gravity-aligned RGB reconstruction factors multi-view scenes into rigid object meshes with 6-DoF poses plus a cleaned background for direct physics simulation.
-
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
IVGT implicitly models continuous neural scene representations from pose-free multi-view images to enable coherent surface extraction, novel view synthesis, and related 3D tasks via SDF and color prediction.
-
First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction
FSTM improves indoor reconstruction by training geometry first without semantic supervision, then adding semantics, achieving 2.3x faster training and higher object surface recall than joint optimization.
-
A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction
GAI-NeRF combines geometric algebra attention and an adaptive ray tracing module inside a NeRF model to deliver more accurate and generalizable wireless channel predictions across varied indoor environments.
-
Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation
Hitem3D 2.0 combines multi-view image synthesis with native 3D texture projection to improve completeness, cross-view consistency, and geometry alignment over prior methods.
-
TACO: Temporal Consensus Optimization for Continual Neural Mapping
TACO is a replay-free continual neural-mapping method using importance-weighted consensus with past model snapshots to preserve stable geometry while revising outdated regions — validated quantitatively on static scenes, qualitatively on dynamic ones.
-
MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
MetroGS combines distributed 2D Gaussian Splatting with structured dense enhancement, progressive hybrid optimization, and depth-guided appearance modeling to deliver higher geometric accuracy and stability in large-scale urban reconstruction.
-
Geometry-Aware Scene Configurations for Novel View Synthesis
Geometry-guided adaptive placement of bases and virtual viewpoints improves rendering quality and memory use over uniform arrangements in scalable NeRF for large indoor scenes.
-
DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation
LGAA is a modular adapter framework that lifts multi-view diffusion models to produce 2D Gaussian Splats with PBR channels for high-quality relightable 3D mesh extraction using data-efficient finetuning on 69k instances.
-
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
-
A Geometric Algorithm for Blood Vessel Reconstruction from Skeletal Representation
A geometric algorithm reconstructs tubular shapes from skeletal points as a TSDF in voxel hashing using direct geometric distance computation without segmentation or matrix solving.
-
Attention Is not Everything: Efficient Alternatives for Vision
A survey that taxonomizes non-Transformer vision models and evaluates their practical trade-offs across efficiency, scalability, and robustness.
- Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry