mlsanityData to 7 Oct 2026

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

arXiv 2303.02091 ↗First posted 3 Mar 2023cs.CVcited by 106

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support from common 3D software and hardware, making their rendering and manipulation inefficient. To overcome this limitation, we present a novel framework that generates textured surface meshes from images. Our approach begins by efficiently initializing the geometry and view-dependency decomposed appearance with a NeRF. Subsequently, a coarse mesh is extracted, and an iterative surface refining algorithm is developed to adaptively adjust both vertex positions and face density based on re-projected rendering errors. We jointly refine the appearance with geometry and bake it into texture images for real-time rendering. Extensive experiments demonstrate that our method achieves superior mesh quality and competitive rendering quality.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Builds on 49 of its 61 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

49 of 61 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  9. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  11. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
37 more
  1. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  2. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  3. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  4. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  5. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  6. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  7. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  8. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  9. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  10. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  11. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  12. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  13. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  14. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  15. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  16. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  17. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  18. 2021Editing Conditional Radiance Fieldscited by 222
  19. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  20. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  21. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  22. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  23. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  24. 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 173
  25. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  26. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 141
  27. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  28. 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
  29. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  30. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  31. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 92
  32. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  33. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  34. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  35. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  36. 2022Real-Time Neural Light Field on Mobile Devicescited by 48
  37. 2022Neural Density-Distance Fieldscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 19; 2024: 59; 2025: 24; 2026: 4.

106 papers.

Sort:

By area:

  1. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  3. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  4. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  5. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  6. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  7. 2023TextMesh: Generation of Realistic 3D Meshes From Text Promptscited by 135
  8. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 110
  9. 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 78
  10. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
  11. 20243DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priorscited by 72
  12. 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
38 more
  1. 2024Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesiscited by 41
  2. 2024Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generationcited by 32
  3. 2025DRAWER: Digital Reconstruction and Articulation With Environment Realismcited by 29
  4. 2024Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Videocited by 26
  5. 2023VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesiscited by 25
  6. 2023Uncovering and Quantifying Social Biases in Code Generationcited by 25
  7. 2023NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Supportcited by 25
  8. 2023Towards Transferable Targeted 3D Adversarial Attack in the Physical Worldcited by 25
  9. 2023Interactive Segment Anything NeRF with Feature Imitationcited by 24
  10. 2023ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretrainingcited by 24
  11. 2024UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstructioncited by 23
  12. 2023VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streamscited by 22
  13. 2024Mani-GS: Gaussian Splatting Manipulation with Triangular Meshcited by 22
  14. 2024Thermal-NeRF: Neural Radiance Fields from an Infrared Cameracited by 21
  15. 2025LinPrim: Linear Primitives for Differentiable Volumetric Renderingcited by 21
  16. 2024MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Renderingcited by 19
  17. 2024RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussianscited by 16
  18. 2023NTO3D: Neural Target Object 3D Reconstruction with Segment Anythingcited by 14
  19. 2023City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Webcited by 14
  20. 2024HPC: Hierarchical Progressive Coding Framework for Volumetric Videocited by 13
  21. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  22. 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priorscited by 11
  23. 2024AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphonescited by 10
  24. 2025TACO: Taming Diffusion for in-the-wild Video Amodal Completioncited by 10
  25. 2024Anything in Any Scene: Photorealistic Video Object Insertioncited by 9
  26. 2024TexRO: Generating Delicate Textures of 3D Models by Recursive Optimizationcited by 9
  27. 2024Direct and Adaptable Mesh-Gaussian Scene Reconstruction from Multi-View Imagescited by 9
  28. 2023LightSpeed: Light and Fast Neural Light Fields on Mobile Devicescited by 8
  29. 2024MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splattingcited by 8
  30. 2024MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Resultscited by 8
  31. 2024A Simple Approach to Differentiable Rendering of SDFscited by 7
  32. 20243D Gaussian Editing with A Single Imagecited by 7
  33. 2025GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Modelscited by 7
  34. 2024OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctreescited by 6
  35. 2024CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesiscited by 6
  36. 2024Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussianscited by 6
  37. 2024Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generationcited by 5
  38. 2024SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objectscited by 5

50 most cited of 106 All 106 (JSON)