# KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

arXiv: https://arxiv.org/abs/2205.04992 · HTML: https://mlsanity.com/paper/2205.04992/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 76 references that are in the map.
- First posted on arXiv 10 May 2022.

## Builds on (most cited first, 30 of 56)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes](https://mlsanity.com/paper/2104.06935/) (2021)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [Deep Appearance Models for Face Rendering](https://mlsanity.com/paper/1808.00362/) (2018)

## Built on by (most cited first, 30 of 77)

- [GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis](https://mlsanity.com/paper/2312.02155/) (2023)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [ARAH: Animatable Volume Rendering of Articulated Human SDFs](https://mlsanity.com/paper/2210.10036/) (2022)
- [Drivable 3D Gaussian Avatars](https://mlsanity.com/paper/2311.08581/) (2023)
- [DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering](https://mlsanity.com/paper/2307.10173/) (2023)
- [NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild](https://mlsanity.com/paper/2405.18715/) (2024)
- [Learning Neural Volumetric Representations of Dynamic Humans in Minutes](https://mlsanity.com/paper/2302.12237/) (2023)
- [OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering](https://mlsanity.com/paper/2303.14662/) (2023)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting](https://mlsanity.com/paper/2312.02902/) (2023)
- [SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling](https://mlsanity.com/paper/2303.17368/) (2023)
- [SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction](https://mlsanity.com/paper/2409.11211/) (2024)
- [RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars](https://mlsanity.com/paper/2305.13353/) (2023)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [Single-Image 3D Human Digitization with Shape-Guided Diffusion](https://mlsanity.com/paper/2311.09221/) (2023)
- [TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer](https://mlsanity.com/paper/2211.10705/) (2022)
- [Generalizable Human Gaussians for Sparse View Synthesis](https://mlsanity.com/paper/2407.12777/) (2024)
- [Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis](https://mlsanity.com/paper/2309.16859/) (2023)
- [HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field](https://mlsanity.com/paper/2309.17128/) (2023)
- [DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis](https://mlsanity.com/paper/2310.11449/) (2023)
- [HHAvatar: Gaussian Head Avatar with Dynamic Hairs](https://mlsanity.com/paper/2312.03029/) (2023)
- [NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation](https://mlsanity.com/paper/2212.00613/) (2022)
- [AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars](https://mlsanity.com/paper/2306.00547/) (2023)
- [Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors](https://mlsanity.com/paper/2208.11905/) (2022)
- [HARP: Personalized Hand Reconstruction from a Monocular RGB Video](https://mlsanity.com/paper/2212.09530/) (2022)
- [NPC: Neural Point Characters from Video](https://mlsanity.com/paper/2304.02013/) (2023)
- [GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images](https://mlsanity.com/paper/2303.13777/) (2023)
- [Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation](https://mlsanity.com/paper/2401.04728/) (2024)
- [Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input](https://mlsanity.com/paper/2310.05917/) (2023)
- [DINER: Depth-aware Image-based NEural Radiance fields](https://mlsanity.com/paper/2211.16630/) (2022)

## Abstract (arXiv)

Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambiguity. However, global encodings often suffer from overfitting to the distribution of the training data, and it is difficult to learn multi-view consistent reconstruction from sparse views. In this work, we investigate common issues with existing spatial encodings and propose a simple yet highly effective approach to modeling high-fidelity volumetric humans from sparse views. One of the key ideas is to encode relative spatial 3D information via sparse 3D keypoints. This approach is robust to the sparsity of viewpoints and cross-dataset domain gap. Our approach outperforms state-of-the-art methods for head reconstruction. On human body reconstruction for unseen subjects, we also achieve performance comparable to prior work that uses a parametric human body model and temporal feature aggregation. Our experiments show that a majority of errors in prior work stem from an inappropriate choice of spatial encoding and thus we suggest a new direction for high-fidelity image-based human modeling. https://markomih.github.io/KeypointNeRF