mlsanityData to 14 Oct 2026

HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis

arXiv 2508.09137 ↗First posted 12 Aug 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Simultaneous relighting and novel-view rendering of digital human representations is an important yet challenging task with numerous applications. Progress in this area has been significantly limited due to the lack of publicly available, high-quality datasets, especially for full-body human captures. To address this critical gap, we introduce the HumanOLAT dataset, the first publicly accessible large-scale dataset of multi-view One-Light-at-a-Time (OLAT) captures of full-body humans. The dataset includes HDR RGB frames under various illuminations, such as white light, environment maps, color gradients and fine-grained OLAT illuminations. Our evaluations of state-of-the-art relighting and novel-view synthesis methods underscore both the dataset's value and the significant challenges still present in modeling complex human-centric appearance and lighting interactions. We believe HumanOLAT will significantly facilitate future research, enabling rigorous benchmarking and advancements in both general and human-specific relighting and rendering techniques.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 42 of its 64 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

42 of 64 references.

References · 42

  1. 2023Segment Anythingcited by 8,234
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  6. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  7. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  8. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  9. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  10. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  11. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  12. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 224
30 more
  1. 2019Single Image Portrait Relightingcited by 152
  2. 2023Relightable Gaussian Codec Avatarscited by 127
  3. 2023GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorizationcited by 87
  4. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 67
  5. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  6. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  7. 2021Neural Video Portrait Relighting in Real-time via Consistency Modelingcited by 46
  8. 2024GS^3: Efficient Relighting with Triple Gaussian Splattingcited by 44
  9. 2024URAvatar: Universal Relightable Gaussian Codec Avatarscited by 43
  10. 2023ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objectscited by 42
  11. 2024GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Renderingcited by 42
  12. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 41
  13. 2024DifFRelight: Diffusion-Based Facial Performance Relightingcited by 35
  14. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  15. 2023Towards Practical Capture of High-Fidelity Relightable Avatarscited by 34
  16. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  17. 2023OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objectscited by 31
  18. 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
  19. 2023Animatable and Relightable Gaussians for High-fidelity Human Avatar Modelingcited by 27
  20. 2025Relightable Full-Body Gaussian Codec Avatarscited by 22
  21. 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Modelscited by 21
  22. 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
  23. 2024URHand: Universal Relightable Handscited by 17
  24. 2024RNG: Relightable Neural Gaussianscited by 16
  25. 2023Relightable and Animatable Neural Avatars from Videoscited by 13
  26. 2023Relightable Neural Actor with Intrinsic Decomposition and Pose Controlcited by 11
  27. 2024GUS-IR: Gaussian Splatting with Unified Shading for Inverse Renderingcited by 11
  28. 2024BiGS: Bidirectional Gaussian Primitives for Relightable 3D Gaussian Splattingcited by 8
  29. 2024PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfercited by 4
  30. 2025OMG: Opacity Matters in Material Modeling with Gaussian Splattingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Controlcited by 5
  2. 2025Bringing Your Portrait to 3D Presencecited by 3
  3. 2026GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformerscited by 3
  4. 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gapcited by 1
  5. 2025POLAR: A Portrait OLAT Dataset and Generative Framework for Illumination-Aware Face Modelingcited by 1
  6. 2026WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relightingcited by 0
  7. 2026AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Texturescited by 0