# DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

arXiv: https://arxiv.org/abs/2310.11449 · HTML: https://mlsanity.com/paper/2310.11449/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 65 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [TAVA: Template-free Animatable Volumetric Actors](https://mlsanity.com/paper/2206.08929/) (2022)
- [Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering](https://mlsanity.com/paper/2109.07448/) (2021)
- [H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion](https://mlsanity.com/paper/2110.13746/) (2021)
- [Editable Free-viewpoint Video Using a Layered Neural Representation](https://mlsanity.com/paper/2104.14786/) (2021)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [ARAH: Animatable Volume Rendering of Articulated Human SDFs](https://mlsanity.com/paper/2210.10036/) (2022)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video](https://mlsanity.com/paper/2210.06108/) (2022)
- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [Animatable Neural Radiance Fields from Monocular RGB Videos](https://mlsanity.com/paper/2106.13629/) (2021)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [Driving-Signal Aware Full-Body Avatars](https://mlsanity.com/paper/2105.10441/) (2021)
- [KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints](https://mlsanity.com/paper/2205.04992/) (2022)
- [Textured Neural Avatars](https://mlsanity.com/paper/1905.08776/) (2019)
- [Learning Neural Light Fields with Ray-Space Embedding Networks](https://mlsanity.com/paper/2112.01523/) (2021)

## Built on by (most cited first, 30 of 36)

- [3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2312.09228/) (2023)
- [GART: Gaussian Articulated Template Models](https://mlsanity.com/paper/2311.16099/) (2023)
- [ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering](https://mlsanity.com/paper/2312.05941/) (2023)
- [HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting](https://mlsanity.com/paper/2312.03461/) (2023)
- [PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations](https://mlsanity.com/paper/2404.04421/) (2024)
- [Generalizable Human Gaussians for Sparse View Synthesis](https://mlsanity.com/paper/2407.12777/) (2024)
- [MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos](https://mlsanity.com/paper/2407.08414/) (2024)
- [Human101: Training 100+FPS Human Gaussians in 100s from 1 View](https://mlsanity.com/paper/2312.15258/) (2023)
- [Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos](https://mlsanity.com/paper/2409.08353/) (2024)
- [TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis](https://mlsanity.com/paper/2312.05161/) (2023)
- [Animatable and Relightable Gaussians for High-fidelity Human Avatar Modeling](https://mlsanity.com/paper/2311.16096/) (2023)
- [ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation](https://mlsanity.com/paper/2412.18600/) (2024)
- [VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams](https://mlsanity.com/paper/2312.01407/) (2023)
- [Expressive Gaussian Human Avatars from Monocular RGB Video](https://mlsanity.com/paper/2407.03204/) (2024)
- [GAS: Generative Avatar Synthesis from a Single Image](https://mlsanity.com/paper/2502.06957/) (2025)
- [Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras](https://mlsanity.com/paper/2312.07423/) (2023)
- [PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image](https://mlsanity.com/paper/2508.09973/) (2025)
- [SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets](https://mlsanity.com/paper/2504.06982/) (2025)
- [Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs](https://mlsanity.com/paper/2504.12909/) (2025)
- [Relightable Neural Actor with Intrinsic Decomposition and Pose Control](https://mlsanity.com/paper/2312.11587/) (2023)
- [MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering](https://mlsanity.com/paper/2403.18820/) (2024)
- [EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars](https://mlsanity.com/paper/2410.01835/) (2024)
- [RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance](https://mlsanity.com/paper/2503.12242/) (2025)
- [Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures](https://mlsanity.com/paper/2412.13183/) (2024)
- [RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians](https://mlsanity.com/paper/2501.07104/) (2025)
- [UMA: Ultra-detailed Human Avatars via Multi-level Surface Alignment](https://mlsanity.com/paper/2506.01802/) (2025)
- [High-Fidelity Mobile Avatars with Pruned Local Blendshapes](https://mlsanity.com/paper/2605.01854/) (2026)
- [TEDRA: Text-based Editing of Dynamic and Photoreal Actors](https://mlsanity.com/paper/2408.15995/) (2024)
- [EfficientHuman: Efficient Training and Reconstruction of Moving Human using Articulated 2D Gaussian](https://mlsanity.com/paper/2504.20607/) (2025)
- [Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion](https://mlsanity.com/paper/2509.04145/) (2025)

## Abstract (arXiv)

Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time. The video results and code are available at https://vcai.mpi-inf.mpg.de/projects/DELIFFAS.