mlsanityData to 14 Oct 2026

Designing Deep Networks for Surface Normal Estimation

arXiv 1411.4958 ↗First posted 18 Nov 2014cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture we should use? We propose to build upon the decades of hard work in 3D scene understanding, to design new CNN architecture for the task of surface normal estimation. We show by incorporating several constraints (man-made, manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Nov 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 8; 2023: 8; 2024: 15; 2025: 10; 2026: 3.

59 papers.

Sort:

By area:

  1. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  2. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  3. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  4. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 154
  5. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 124
  6. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  7. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Thinkcited by 83
  8. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  9. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  10. 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
  11. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  12. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
38 more
  1. 2025Dens3R: A Foundation Model for 3D Geometry Predictioncited by 46
  2. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  3. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  4. 2021Shape and Material Capture at Homecited by 36
  5. 2021StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationcited by 36
  6. 2022Understanding 3D Object Articulation in Internet Videoscited by 36
  7. 2021RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depthcited by 33
  8. 2023Understanding 3D Object Interaction from a Single Imagecited by 33
  9. 2022IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertaintycited by 30
  10. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  11. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  12. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generationcited by 17
  13. 2023A step towards understanding why classification helps regressioncited by 15
  14. 2023PolyMaX: General Dense Prediction with Mask Transformercited by 14
  15. 2024Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Imagescited by 14
  16. 2022DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Modelscited by 12
  17. 2024Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priorscited by 11
  18. 2022Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimationcited by 10
  19. 2023NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completioncited by 9
  20. 2021CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameterscited by 8
  21. 2021What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstructioncited by 7
  22. 2023Convex Decomposition of Indoor Scenescited by 7
  23. 2024Digging Into Normal Incorporated Stereo Matchingcited by 5
  24. 2024GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Modelscited by 5
  25. 2025Multi-view Surface Reconstruction Using Normal and Reflectance Cuescited by 5
  26. 2024On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimationcited by 4
  27. 2024Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Modelscited by 4
  28. 2021Streaming Self-Training via Domain-Agnostic Unlabeled Imagescited by 3
  29. 2021Sketch-based Normal Map Generation with Geometric Samplingcited by 3
  30. 2021Feature Pyramid Network for Multi-task Affective Analysiscited by 3
  31. 2023Consistent Multimodal Generation via A Unified GAN Frameworkcited by 3
  32. 2021FloorLevel-Net: Recognizing Floor-Level Lines with Height-Attention-Guided Multi-task Learningcited by 2
  33. 2023Learning to Predict Scene-Level Implicit 3D from Posed RGBD Datacited by 2
  34. 2026Monocular Normal Estimation via Shading Sequence Estimationcited by 2
  35. 2022Neural Network Normal Estimation and Bathymetry Reconstruction from Sidescan Sonarcited by 1
  36. 2023Multi-Task Self-Supervised Learning for Image Segmentation Taskcited by 1
  37. 2024Improved Convex Decomposition with Ensembling and Negative Primitivescited by 1
  38. 2025Joint Learning of Depth and Appearance for Portrait Image Animationcited by 1

50 most cited of 59 All 59 (JSON)