# HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion

arXiv: https://arxiv.org/abs/2305.06356 · HTML: https://mlsanity.com/paper/2305.06356/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 72 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 30 of 42)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [DynIBaR: Neural Dynamic Image-Based Rendering](https://mlsanity.com/paper/2211.11082/) (2022)
- [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](https://mlsanity.com/paper/2104.03953/) (2021)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time](https://mlsanity.com/paper/2202.08614/) (2022)

## Built on by (most cited first, 30 of 161)

- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Drivable 3D Gaussian Avatars](https://mlsanity.com/paper/2311.08581/) (2023)
- [Human Gaussian Splatting: Real-time Rendering of Animatable Avatars](https://mlsanity.com/paper/2311.17113/) (2023)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering](https://mlsanity.com/paper/2312.05941/) (2023)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering](https://mlsanity.com/paper/2307.10173/) (2023)
- [DreamHuman: Animatable 3D Avatars from Text](https://mlsanity.com/paper/2306.09329/) (2023)
- [4K4D: Real-Time 4D View Synthesis at 4K Resolution](https://mlsanity.com/paper/2310.11448/) (2023)
- [Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos](https://mlsanity.com/paper/2412.09621/) (2024)
- [HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting](https://mlsanity.com/paper/2312.03461/) (2023)
- [AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose](https://mlsanity.com/paper/2308.03610/) (2023)
- [Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes](https://mlsanity.com/paper/2310.08585/) (2023)
- [IDOL: Instant Photorealistic 3D Human Creation from a Single Image](https://mlsanity.com/paper/2412.14963/) (2024)
- [MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures](https://mlsanity.com/paper/2312.02963/) (2023)
- [4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations](https://mlsanity.com/paper/2404.18630/) (2024)
- [PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations](https://mlsanity.com/paper/2404.04421/) (2024)
- [SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2312.13308/) (2023)
- [NPGA: Neural Parametric Gaussian Avatars](https://mlsanity.com/paper/2405.19331/) (2024)
- [Deformable 3D Gaussian Splatting for Animatable Human Avatars](https://mlsanity.com/paper/2312.15059/) (2023)
- [GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting](https://mlsanity.com/paper/2401.09720/) (2024)
- [MonoNPHM: Dynamic Head Reconstruction from Monocular Videos](https://mlsanity.com/paper/2312.06740/) (2023)
- [MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos](https://mlsanity.com/paper/2407.08414/) (2024)
- [Control4D: Efficient 4D Portrait Editing with Text](https://mlsanity.com/paper/2305.20082/) (2023)
- [HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior](https://mlsanity.com/paper/2404.01053/) (2024)
- [Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos](https://mlsanity.com/paper/2409.08353/) (2024)

## Abstract (arXiv)

Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the gap to production-level quality, we introduce HumanRF, a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints. Our novel representation acts as a dynamic video encoding that captures fine details at high compression rates by factorizing space-time into a temporal matrix-vector decomposition. This allows us to obtain temporally coherent reconstructions of human actors for long sequences, while representing high-resolution details even in the context of challenging motion. While most research focuses on synthesizing at resolutions of 4MP or lower, we address the challenge of operating at 12MP. To this end, we introduce ActorsHQ, a novel multi-view dataset that provides 12MP footage from 160 cameras for 16 sequences with high-fidelity, per-frame mesh reconstructions. We demonstrate challenges that emerge from using such high-resolution data and show that our newly introduced HumanRF effectively leverages this data, making a significant step towards production-level quality novel view synthesis.