mlsanityData to 7 Oct 2026

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

arXiv 2310.16044 ↗First posted 24 Oct 2023cs.CV cs.GRcited by 51

Not on the map. Why?

Abstract (arXiv)

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark. Recent advances in inverse rendering have enabled a wide range of real-world applications in 3D content generation, moving rapidly from research and commercial use cases to consumer devices. While the results continue to improve, there is no real-world benchmark that can quantitatively assess and compare the performance of various inverse rendering methods. Existing real-world datasets typically only consist of the shape and multi-view images of objects, which are not sufficient for evaluating the quality of material recovery and object relighting. Methods capable of recovering material and lighting often resort to synthetic data for quantitative evaluation, which on the other hand does not guarantee generalization to complex real-world environments. We introduce a new dataset of real-world objects captured under a variety of natural scenes with ground-truth 3D scans, multi-view images, and environment lighting. Using this dataset, we establish the first comprehensive real-world evaluation benchmark for object inverse rendering tasks from in-the-wild scenes, and compare the performance of various existing methods.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 61 of its 89 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

61 of 89 references.

References · 61

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2023Segment Anythingcited by 8,158
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  6. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  11. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  12. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
38 more
  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  2. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  3. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  4. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  5. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  6. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  7. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  8. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 202
  9. 2022Modeling Indirect Illumination for Inverse Renderingcited by 167
  10. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  11. 2021NeRF for Outdoor Scene Relightingcited by 114
  12. 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 110
  13. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  14. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  15. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  16. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  17. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 78
  18. 2020OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasetscited by 73
  19. 2021Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Renderingcited by 71
  20. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  21. 2020Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Imagescited by 65
  22. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  23. 2020Two-shot Spatially-varying BRDF and Shape Estimationcited by 59
  24. 2020Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materialscited by 56
  25. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  26. 2021Self-supervised Outdoor Scene Relightingcited by 48
  27. 2023Neural-PBIR Reconstruction of Shape, Material, and Illuminationcited by 45
  28. 2017Self-Supervised Intrinsic Image Decompositioncited by 43
  29. 2022Reinforcement Learning with Neural Radiance Fieldscited by 43
  30. 2016Learning Non-Lambertian Object Intrinsics across ShapeNet Categoriescited by 42
  31. 2023ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objectscited by 42
  32. 2020Learning 3D Dynamic Scene Representations for Robot Manipulationcited by 39
  33. 2023NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illuminationcited by 38
  34. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  35. 2020Learning to Factorize and Relight a Citycited by 36
  36. 2022NeROIC: Neural Rendering of Objects from Online Image Collectionscited by 36
  37. 2022Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objectscited by 36
  38. 2022De-rendering 3D Objects in the Wildcited by 31

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 18; 2026: 17.

51 papers.

Sort:

By area:

  1. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 40
  2. 2024GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Renderingcited by 39
  3. 2024IllumiNeRF: 3D Relighting Without Inverse Renderingcited by 29
  4. 2025Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Datasetcited by 29
  5. 2024MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priorscited by 28
  6. 2024RelitLRM: Generative Relightable Radiance for Large Reconstruction Modelscited by 23
  7. 2024GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Renderingcited by 22
  8. 2024IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminationscited by 21
  9. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Capturescited by 19
  10. 2025UnCommon Objects in 3Dcited by 17
  11. 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fieldscited by 16
  12. 2024ReCap: Better Gaussian Relighting with Cross-Environment Capturescited by 14
38 more
  1. 2024GlossyGS: Inverse Rendering of Glossy Objects with 3D Gaussian Splattingcited by 13
  2. 2024Flash Cache: Reducing Bias in Radiance Cache Based Inverse Renderingcited by 12
  3. 2025UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedbackcited by 12
  4. 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstructioncited by 11
  5. 2024GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstructioncited by 10
  6. 2024SuperMat: Physically Consistent PBR Material Estimation at Interactive Ratescited by 9
  7. 2025RTR-GS: 3D Gaussian Splatting for Inverse Rendering with Radiance Transfer and Reflectioncited by 9
  8. 2025ROGR: Relightable 3D Objects using Generative Relightingcited by 7
  9. 2025SViM3D: Stable Video Material Diffusion for Single Image 3D Generationcited by 7
  10. 2025TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimizationcited by 6
  11. 2024Progressive Radiance Distillation for Inverse Rendering with Gaussian Splattingcited by 5
  12. 2025PolarAnything: Diffusion-based Polarimetric Image Synthesiscited by 5
  13. 2025OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Controlcited by 5
  14. 2025A Real-world Display Inverse Rendering Datasetcited by 4
  15. 2026LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditionscited by 4
  16. 2024PBIR-NIE: Glossy Object Capture under Non-Distant Lightingcited by 3
  17. 2025Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstructioncited by 3
  18. 2025Twinner: Shining Light on Digital Twins in a Few Snapscited by 2
  19. 2025StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimationcited by 2
  20. 2025MatMart: Material Reconstruction of 3D Objects via Diffusioncited by 2
  21. 2026Radiometrically Consistent Gaussian Surfels for Inverse Renderingcited by 2
  22. 2026LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windowscited by 2
  23. 2025Generative Perception of Shape and Material from Differential Motioncited by 1
  24. 2026ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illuminationcited by 1
  25. 2026LumiMotion: Improving Gaussian Relighting with Scene Dynamicscited by 1
  26. 2026F-RNG: Feed-Forward Relightable Neural Gaussianscited by 1
  27. 2024OpenMaterial: A Large-scale Dataset of Complex Materials for 3D Reconstructioncited by 0
  28. 2024An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstructioncited by 0
  29. 2025Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimizationcited by 0
  30. 2026EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setupscited by 0
  31. 2026Under One Sun: Multi-Object Generative Perception of Materials and Illuminationcited by 0
  32. 20263DSS: 3D Surface Splatting for Inverse Renderingcited by 0
  33. 2026WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relightingcited by 0
  34. 2026Ambient-robust Inverse Rendering using Active RGB-NIR Imagingcited by 0
  35. 2026DANTE-W: Diffuse Albedo Neural Texturing in the Wildcited by 0
  36. 2026Diffusion-Based Material Regularization for Physics-Based Inverse Renderingcited by 0
  37. 2026ExMesh++: From Multi-View Images to Relightable UV-PBR Mesh Assets via Topology-Adaptive Reconstruction and Decompositioncited by 0
  38. 2026RelightFormer: Feed-forward Generative Transformer for Multiview Object Relightingcited by 0

50 most cited of 51 All 51 (JSON)