mlsanityData to 7 Oct 2026

InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video

arXiv 2411.01512 ↗First posted 3 Nov 2024cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars. Our key observation is that the optimization of a hash grid encoding to represent a signed distance function (SDF) of the human subject is fraught with instabilities and bad local minima. We thus propose a principled geometry-aware SDF regularization scheme that seamlessly fits into the volume rendering pipeline and adds negligible computational overhead. Our regularization scheme significantly outperforms previous approaches for training SDFs on hash grids. We obtain competitive results in geometry reconstruction and novel view synthesis in as little as five minutes of training time, a significant reduction from the several hours required by previous work. InstantGeoAvatar represents a significant leap forward towards achieving interactive reconstruction of virtual avatars.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 95 of its 123 references that are in the map. First posted on arXiv 3 Nov 2024.

Builds on

95 of 123 references.

References · 95

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  4. 2018On the Spectral Bias of Neural Networkscited by 1,321
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  9. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  10. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  11. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  12. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
38 more
  1. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  2. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  3. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  4. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  5. 2018Video Based Reconstruction of 3D People Modelscited by 237
  6. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  7. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  8. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  9. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  10. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  11. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  12. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  13. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  14. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  15. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  16. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  17. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  18. 2022Instant Volumetric Head Avatarscited by 157
  19. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  20. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  21. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  22. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  23. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  24. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  25. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  26. 2018Detailed Human Avatars from Monocular Videocited by 109
  27. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  28. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  29. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  30. 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
  31. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  32. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  33. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  34. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
  35. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  36. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  37. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  38. 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 66

50 most cited of 95 All 95 (JSON)

Built on by

Not cited yet.