mlsanityData to 7 Oct 2026

Rethinking Inductive Biases for Surface Normal Estimation

arXiv 2403.00712 ↗First posted 1 Mar 2024cs.CVcited by 122

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks. In this paper, we discuss the inductive biases needed for surface normal estimation and propose to (1) utilize the per-pixel ray direction and (2) encode the relationship between neighboring surface normals by learning their relative rotation. The proposed method can generate crisp - yet, piecewise smooth - predictions for challenging in-the-wild images of arbitrary resolution and aspect ratio. Compared to a recent ViT-based state-of-the-art model, our method shows a stronger generalization ability, despite being trained on an orders of magnitude smaller dataset. The code is available at https://github.com/baegwangbin/DSINE.

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 1 Mar 2024.

Builds on

42 of 66 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2021Vision Transformers for Dense Predictioncited by 1,789
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  11. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  12. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
30 more
  1. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  2. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  3. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  4. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  5. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  6. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  7. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  8. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  9. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  10. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  11. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  12. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  13. 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 137
  14. 20193D Ken Burns Effect from a Single Imagecited by 128
  15. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  16. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  17. 20223D Common Corruptions and Data Augmentationcited by 120
  18. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  19. 2020Robust Learning Through Cross-Task Consistencycited by 105
  20. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  21. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  22. 2014Designing Deep Networks for Surface Normal Estimationcited by 59
  23. 2021SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Datacited by 38
  24. 2016Marr Revisited: 2D-3D Alignment via Surface Normal Predictioncited by 34
  25. 2020Surface Normal Estimation of Tilted Images via Spatial Rectifiercited by 34
  26. 2022IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertaintycited by 30
  27. 2023Prismer: A Vision-Language Model with Multi-Task Expertscited by 28
  28. 2022MonoGraspNet: 6-DoF Grasping with a Single RGB Imagecited by 24
  29. 2022SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB imagecited by 19
  30. 2023FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Datacited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 29; 2025: 53; 2026: 40.

122 papers.

Sort:

By area:

  1. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  2. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  3. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163
  4. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 153
  5. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  6. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  7. 2025TesserAct: Learning 4D Embodied World Modelscited by 90
  8. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Thinkcited by 82
  9. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  10. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  11. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 60
  12. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
38 more
  1. 2025Dens3R: A Foundation Model for 3D Geometry Predictioncited by 44
  2. 2026Image Generators are Generalist Vision Learnerscited by 40
  3. 2025DICEPTION: A Generalist Diffusion Model for Visual Perceptual Taskscited by 37
  4. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  5. 2024EnvGS: Modeling View-Dependent Appearance with Environment Gaussiancited by 34
  6. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  7. 2024PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructionscited by 31
  8. 2025DRAWER: Digital Reconstruction and Articulation With Environment Realismcited by 29
  9. 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Videocited by 27
  10. 2024Feat2GS: Probing Visual Foundation Models with Gaussian Splattingcited by 26
  11. 2025NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priorscited by 25
  12. 2025MP-SfM: Monocular Surface Priors for Robust Structure-from-Motioncited by 25
  13. 2024HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstructioncited by 24
  14. 2024ScribbleLight: Single Image Indoor Relighting with Scribblescited by 22
  15. 2025CADDreamer: CAD Object Generation from Single-view Imagescited by 22
  16. 2024LaVin-DiT: Large Vision Diffusion Transformercited by 21
  17. 2025VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotioncited by 20
  18. 2025From Editor to Dense Geometry Estimatorcited by 20
  19. 2024Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusioncited by 19
  20. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generationcited by 17
  21. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  22. 2024PuzzleAvatar: Assembling 3D Avatars from Personal Albumscited by 16
  23. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  24. 2024DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Posescited by 16
  25. 2025Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Modelcited by 16
  26. 2025GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstructioncited by 15
  27. 2025RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splattingcited by 12
  28. 2025Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinatescited by 12
  29. 2024Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priorscited by 11
  30. 2025GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstructioncited by 11
  31. 2025DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Renderingcited by 11
  32. 2025EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Devicecited by 11
  33. 2025GLaD: Geometric Latent Distillation for Vision-Language-Action Modelscited by 10
  34. 2024GLS: Geometry-aware 3D Language Gaussian Splattingcited by 9
  35. 2025UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimationcited by 9
  36. 2024Diffusion Models are Efficient Data Generators for Human Mesh Recoverycited by 8
  37. 2026Generative World Renderercited by 8
  38. 2024DPBridge: Latent Diffusion Bridge for Dense Predictioncited by 6

50 most cited of 122 All 122 (JSON)