mlsanityData to 7 Oct 2026

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds

arXiv 2212.10550 ↗First posted 20 Dec 2022cs.CVcited by 138

Not on the map. Why?

Abstract (arXiv)

In this paper, we take a significant step towards real-world applicability of monocular neural avatar reconstruction by contributing InstantAvatar, a system that can reconstruct human avatars from a monocular video within seconds, and these avatars can be animated and rendered at an interactive rate. To achieve this efficiency we propose a carefully designed and engineered system, that leverages emerging acceleration structures for neural fields, in combination with an efficient empty space-skipping strategy for dynamic scenes. We also contribute an efficient implementation that we will make available for research purposes. Compared to existing methods, InstantAvatar converges 130x faster and can be trained in minutes instead of hours. It achieves comparable or even better reconstruction quality and novel pose synthesis results. When given the same time budget, our method significantly outperforms SoTA methods. InstantAvatar can yield acceptable visual quality in as little as 10 seconds training time.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). Builds on 64 of its 79 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

64 of 79 references.

References · 64

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  11. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  12. 2020Neural Sparse Voxel Fieldscited by 959
38 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  2. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  3. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  4. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  5. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  6. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  7. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  8. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  9. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  10. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  11. 2017Learning from Synthetic Humanscited by 358
  12. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  13. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  14. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  15. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  16. 2018Video Based Reconstruction of 3D People Modelscited by 237
  17. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  18. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  19. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  20. 2021Neural Articulated Radiance Fieldcited by 196
  21. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  22. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  23. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  24. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  25. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
  26. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  27. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  28. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  29. 2018Detailed Human Avatars from Monocular Videocited by 109
  30. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  31. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  32. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  33. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  34. 2022Generative Neural Articulated Radiance Fieldscited by 101
  35. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  36. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 89
  37. 2021LOLNeRF: Learn from One Lookcited by 84
  38. 2022Capturing and Animation of Body and Clothing from Monocular Videocited by 83

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 23; 2024: 48; 2025: 40; 2026: 27.

138 papers.

Sort:

By area:

  1. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  2. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
  3. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  4. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  5. 2023HUGS: Human Gaussian Splatscited by 154
  6. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  7. 2023GART: Gaussian Articulated Template Modelscited by 121
  8. 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
  9. 2024Expressive Whole-Body 3D Gaussian Avatarcited by 89
  10. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  11. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  12. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
38 more
  1. 2023AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Posecited by 60
  2. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  3. 2023PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modelingcited by 50
  4. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  5. 2024GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splattingcited by 36
  6. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  7. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  8. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  9. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 30
  10. 2024Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videoscited by 30
  11. 2023Animatable and Relightable Gaussians for High-fidelity Human Avatar Modelingcited by 27
  12. 2024ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generationcited by 25
  13. 2024Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creationcited by 23
  14. 2024GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videoscited by 22
  15. 2024LayGA: Layered Gaussian Avatars for Animatable Clothing Transfercited by 22
  16. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  17. 2024Expressive Gaussian Human Avatars from Monocular RGB Videocited by 21
  18. 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
  19. 2024Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpsescited by 17
  20. 2024iHuman: Instant Animatable Digital Humans From Monocular Videoscited by 17
  21. 2024Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergycited by 16
  22. 2023Animatable 3D Gaussians for High-fidelity Synthesis of Human Motionscited by 15
  23. 2024Towards Multiple Character Image Animation Through Enhancing Implicit Decouplingcited by 15
  24. 2023Rendering Humans from Object-Occluded Monocular Videoscited by 14
  25. 2025HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restorationcited by 13
  26. 2025PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Imagecited by 13
  27. 2023HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Posescited by 12
  28. 2024MultiPly: Reconstruction of Multiple People from Monocular Video in the Wildcited by 12
  29. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  30. 2024DressRecon: Freeform 4D Human Reconstruction from Monocular Videocited by 12
  31. 2025Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPscited by 12
  32. 2024Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequencecited by 11
  33. 2025LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Meshcited by 11
  34. 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splattingcited by 11
  35. 2024DEGAS: Detailed Expressions on Full-Body Gaussian Avatarscited by 10
  36. 2025UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collectionscited by 10
  37. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  38. 2025HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformerscited by 9

50 most cited of 138 All 138 (JSON)