mlsanityData to 7 Oct 2026

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

arXiv 2310.11449 ↗First posted 17 Oct 2023cs.CV cs.GR cs.LGcited by 36

Not on the map. Why?

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.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 39 of its 65 references that are in the map. First posted on arXiv 17 Oct 2023.

Builds on

39 of 65 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2020Neural Sparse Voxel Fieldscited by 959
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  9. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
27 more
  1. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  2. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  3. 2021Neural Articulated Radiance Fieldcited by 196
  4. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  5. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  6. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  7. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  8. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  9. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  10. 2021Real-time Deep Dynamic Characterscited by 133
  11. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  12. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  13. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  14. 2021Light Field Neural Renderingcited by 108
  15. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  16. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  17. 2019Textured Neural Avatarscited by 65
  18. 2021Learning Neural Light Fields with Ray-Space Embedding Networkscited by 49
  19. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  20. 2022DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networkscited by 38
  21. 2021NeuLF: Efficient Novel View Synthesis with Neural 4D Light Fieldcited by 33
  22. 2022Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actorscited by 28
  23. 2023Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Inputcited by 22
  24. 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modelingcited by 19
  25. 2022Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Cameracited by 12
  26. 2022Real-Time Neural Character Rendering with Pose-Guided Multiplane Imagescited by 10
  27. 2022Progressively-connected Light Field Network for Efficient View Synthesiscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 12; 2025: 9; 2026: 5.

36 papers.

Sort:

By area:

  1. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  2. 2023GART: Gaussian Articulated Template Modelscited by 121
  3. 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
  4. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  5. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  6. 2024Generalizable Human Gaussians for Sparse View Synthesiscited by 40
  7. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  8. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  9. 2024Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videoscited by 30
  10. 2023TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesiscited by 28
  11. 2023Animatable and Relightable Gaussians for High-fidelity Human Avatar Modelingcited by 27
  12. 2024ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generationcited by 25
24 more
  1. 2023VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streamscited by 22
  2. 2024Expressive Gaussian Human Avatars from Monocular RGB Videocited by 21
  3. 2025GAS: Generative Avatar Synthesis from a Single Imagecited by 19
  4. 2023Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Camerascited by 17
  5. 2025PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Imagecited by 13
  6. 2025SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assetscited by 12
  7. 2025Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPscited by 12
  8. 2023Relightable Neural Actor with Intrinsic Decomposition and Pose Controlcited by 11
  9. 2024MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Renderingcited by 11
  10. 2025RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformancecited by 8
  11. 2024EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatarscited by 7
  12. 2024Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Texturescited by 7
  13. 2025RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussianscited by 7
  14. 2025UMA: Ultra-detailed Human Avatars via Multi-level Surface Alignmentcited by 3
  15. 2026High-Fidelity Mobile Avatars with Pruned Local Blendshapescited by 2
  16. 2024TEDRA: Text-based Editing of Dynamic and Photoreal Actorscited by 1
  17. 2025EfficientHuman: Efficient Training and Reconstruction of Moving Human using Articulated 2D Gaussiancited by 1
  18. 2025Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusioncited by 1
  19. 2024Garment Animation NeRF with Color Editingcited by 0
  20. 2024InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Videocited by 0
  21. 2026Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understandingcited by 0
  22. 2026MUA: Mobile Ultra-detailed Animatable Avatarscited by 0
  23. 2026DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatarscited by 0
  24. 2026AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Texturescited by 0