NECA: Neural Customizable Human Avatar
Not on the map. Why?
Abstract (arXiv)
Human avatar has become a novel type of 3D asset with various applications. Ideally, a human avatar should be fully customizable to accommodate different settings and environments. In this work, we introduce NECA, an approach capable of learning versatile human representation from monocular or sparse-view videos, enabling granular customization across aspects such as pose, shadow, shape, lighting and texture. The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering. Extensive experiments demonstrate the advantage of our method over the state-of-the-art methods in photorealistic rendering, as well as various editing tasks such as novel pose synthesis and relighting. The code is available at https://github.com/iSEE-Laboratory/NECA.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 53 of its 78 references that are in the map. First posted on arXiv 15 Mar 2024.
Builds on
53 of 78 references.
References · 53
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2021Volume Rendering of Neural Implicit Surfacescited by 990
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
- 2020Implicit Geometric Regularization for Learning Shapescited by 707
- 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
38 more
- 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
- 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
- 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
- 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
- 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
- 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
- 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
- 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
- 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
- 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
- 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
- 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
- 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
- 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
- 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
- 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
- 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
- 2023TensoIR: Tensorial Inverse Renderingcited by 166
- 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
- 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 142
- 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
- 2021Real-time Deep Dynamic Characterscited by 133
- 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
- 2021NeRF for Outdoor Scene Relightingcited by 114
- 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
- 2018InverseRenderNet: Learning single image inverse renderingcited by 100
- 2023Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenescited by 89
- 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
- 2020Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Imagescited by 65
- 2022Fast-SNARF: A Fast Deformer for Articulated Neural Fieldscited by 55
- 2023Learning Locally Editable Virtual Humanscited by 54
- 2023Representing Volumetric Videos as Dynamic MLP Mapscited by 51
- 2023PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modelingcited by 50
- 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
- 2022Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesiscited by 41
- 2022Relighting4D: Neural Relightable Human from Videoscited by 41
- 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
- 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.