mlsanityData to 7 Oct 2026

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

arXiv 2210.01651 ↗First posted 4 Oct 2022cs.CV cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose SelfNeRF, an efficient neural radiance field based novel view synthesis method for human performance. Given monocular self-rotating videos of human performers, SelfNeRF can train from scratch and achieve high-fidelity results in about twenty minutes. Some recent works have utilized the neural radiance field for dynamic human reconstruction. However, most of these methods need multi-view inputs and require hours of training, making it still difficult for practical use. To address this challenging problem, we introduce a surface-relative representation based on multi-resolution hash encoding that can greatly improve the training speed and aggregate inter-frame information. Extensive experimental results on several different datasets demonstrate the effectiveness and efficiency of SelfNeRF to challenging monocular videos.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

29 of 40 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  4. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  5. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  9. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
17 more
  1. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  2. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  3. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  4. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  5. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  6. 2018Video Based Reconstruction of 3D People Modelscited by 237
  7. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  8. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  9. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  10. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  11. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  12. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  13. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 118
  14. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  15. 2021DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Renderingcited by 60
  16. 2022Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesiscited by 41
  17. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 4; 2025: 1.

9 papers.

  1. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  2. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  3. 2023Animatable and Relightable Gaussians for High-fidelity Human Avatar Modelingcited by 27
  4. 2024LayGA: Layered Gaussian Avatars for Animatable Clothing Transfercited by 22
  5. 2023Rendering Humans from Object-Occluded Monocular Videoscited by 14
  6. 2024Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modelingcited by 4
  7. 2024ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Eventscited by 1
  8. 2023UVA: Towards Unified Volumetric Avatar for View Synthesis, Pose rendering, Geometry and Texture Editingcited by 0
  9. 2025DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspectivecited by 0