mlsanityData to 7 Oct 2026

DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering

arXiv 2106.03798 ↗First posted 7 Jun 2021cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling strategy. Moreover, a view-to-view transformer is introduced to fuse multi-view features and learn view-dependent features directly from high-resolution inputs. With the modeling power of DoubleField and the view-to-view transformer, our method significantly improves the reconstruction quality of both geometry and appearance, while supporting direct inference, scene-specific high-resolution finetuning, and fast rendering. The efficacy of DoubleField is validated by the quantitative evaluations on several datasets and the qualitative results in a real-world sparse multi-view system, showing its superior capability for high-quality human model reconstruction and photo-realistic free-viewpoint human rendering. Data and source code will be made public for the research purpose. Please refer to our project page: http://www.liuyebin.com/dbfield/dbfield.html.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 41 of its 68 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

41 of 68 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2017Non-local Neural Networkscited by 2,290
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  10. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  12. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
29 more
  1. 2020Neural Sparse Voxel Fieldscited by 959
  2. 2017End-to-end Recovery of Human Shape and Posecited by 883
  3. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  4. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  7. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  8. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  10. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  11. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  13. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  14. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  15. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  16. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  17. 2018Bilinear Attention Networkscited by 277
  18. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  19. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  20. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  21. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  22. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  23. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  24. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  25. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  26. 2017MonoPerfCap: Human Performance Capture from Monocular Videocited by 63
  27. 2021NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Camerascited by 40
  28. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  29. 2019Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Imagescited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 24; 2024: 9; 2025: 3; 2026: 3.

52 papers.

Sort:

  1. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  2. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  3. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  4. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2022DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenescited by 103
  7. 2024MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modelingcited by 63
  8. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  9. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  10. 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
  11. 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
  12. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
38 more
  1. 2023HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Videocited by 33
  2. 2022AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capturecited by 25
  3. 2023GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Imagescited by 24
  4. 2023Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Streamcited by 23
  5. 2023Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Inputcited by 22
  6. 2024GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Viewscited by 22
  7. 2023ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFscited by 21
  8. 2023NSF: Neural Surface Fields for Human Modeling from Monocular Depthcited by 21
  9. 2023ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesiscited by 17
  10. 2023SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstructioncited by 15
  11. 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
  12. 2022NDF: Neural Deformable Fields for Dynamic Human Modellingcited by 14
  13. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  14. 2024CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Imagescited by 12
  15. 2023Learning Visibility Field for Detailed 3D Human Reconstruction and Relightingcited by 11
  16. 2023Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Surveycited by 11
  17. 2024MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Renderingcited by 11
  18. 2025HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformerscited by 9
  19. 2023textttNePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registrationcited by 8
  20. 2023Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstructioncited by 8
  21. 2023Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Imagescited by 8
  22. 2023Ins-HOI: Instance Aware Human-Object Interactions Recoverycited by 7
  23. 2022Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Texturescited by 6
  24. 2022FastHuman: Reconstructing High-Quality Clothed Human in Minutescited by 6
  25. 2023Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surfacecited by 6
  26. 2023Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representationcited by 6
  27. 2023High-Resolution Volumetric Reconstruction for Clothed Humanscited by 5
  28. 2023R2Human: Real-Time 3D Human Appearance Rendering from a Single Imagecited by 5
  29. 2024DAGSM: Disentangled Avatar Generation with GS-enhanced Meshcited by 5
  30. 2024Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modelingcited by 4
  31. 2024EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse Viewcited by 3
  32. 2022FLNeRF: 3D Facial Landmarks Estimation in Neural Radiance Fieldscited by 2
  33. 2023Evaluate Geometry of Radiance Fields with Low-frequency Color Priorcited by 2
  34. 2023Invertible Neural Skinningcited by 1
  35. 2023Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsingcited by 1
  36. 2025Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objectscited by 1
  37. 2026HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Videocited by 1
  38. 2025GLVD: Guided Learned Vertex Descentcited by 0

50 most cited of 52 All 52 (JSON)