R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars
Not on the map. Why?
Abstract (arXiv)
We present R3-Avatar, incorporating a temporal codebook, to overcome the inability of human avatars to be both animatable and of high-fidelity rendering quality. Existing video-based reconstruction of 3D human avatars either focuses solely on rendering, lacking animation support, or learns a pose-appearance mapping for animating, which degrades under limited training poses or complex clothing. In this paper, we adopt a "record-retrieve-reconstruct" strategy that ensures high-quality rendering from novel views while mitigating degradation in novel poses. Specifically, disambiguating timestamps record temporal appearance variations in a codebook, ensuring high-fidelity novel-view rendering, while novel poses retrieve corresponding timestamps by matching the most similar training poses for augmented appearance. Our R3-Avatar outperforms cutting-edge video-based human avatar reconstruction, particularly in overcoming visual quality degradation in extreme scenarios with limited training human poses and complex clothing.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 77 of its 93 references that are in the map. First posted on arXiv 17 Mar 2025.
Builds on
77 of 93 references.
References · 77
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2017Neural Discrete Representation Learningcited by 4,650
- 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
- 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
- 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
- 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
- 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
- 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
38 more
- 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
- 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
- 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
- 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
- 2018Video Based Reconstruction of 3D People Modelscited by 237
- 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
- 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
- 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
- 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
- 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
- 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
- 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
- 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
- 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
- 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
- 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
- 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
- 2023HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motioncited by 161
- 2023HUGS: Human Gaussian Splatscited by 154
- 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
- 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
- 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
- 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
- 2023GART: Gaussian Articulated Template Modelscited by 121
- 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
- 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
- 2020Blind Face Restoration via Deep Multi-scale Component Dictionariescited by 106
- 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
- 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
- 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
- 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
- 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
- 2024Expressive Whole-Body 3D Gaussian Avatarcited by 89
- 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
- 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
- 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
- 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
- 2023Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenescited by 55
50 most cited of 77 All 77 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.