3D Vision & Pose

3D reconstruction, scene understanding, pose/keypoint estimation.

A topic in the Science corpus, drawn from 420 papers.

Trusted voices in 3D Vision & Pose

Ordered by the trust 3D Vision & Pose's own network concentrates on each researcher, most first.

  1. Jitendra Malik — trusted by 370 researchers here
  2. Andreas Geiger — trusted by 312 researchers here
  3. Jan-Michael Frahm — trusted by 298 researchers here
  4. Johannes L. Schönberger — trusted by 298 researchers here
  5. Adam T. Zemla — trusted by 192 researchers here
  6. Zicheng Liu — trusted by 204 researchers here
  7. Marc Levoy — trusted by 237 researchers here
  8. Brian Curless — trusted by 237 researchers here
  9. Daniel Scharstein — trusted by 207 researchers here
  10. Gunnar Farnebäck — trusted by 163 researchers here
  11. Charles Ruizhongtai Qi — trusted by 232 researchers here
  12. Richard Szeliski — trusted by 186 researchers here

Most-cited papers in 3D Vision & Pose

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Multiple View Geometry in Computer Vision (2001) — 18,671 citations
  2. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (2017, Neural Information Processing Systems) — 14,555 citations
  3. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms (2001) — 8,091 citations
  4. Structure-from-Motion Revisited (2016) — 7,734 citations
  5. ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017) — 5,692 citations
  6. Deep High-Resolution Representation Learning for Human Pose Estimation (2019) — 5,208 citations
  7. KinectFusion: Real-time dense surface mapping and tracking (2011) — 4,655 citations
  8. DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (2019) — 4,653 citations
  9. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition) — 4,599 citations
  10. A benchmark for the evaluation of RGB-D SLAM systems (2012) — 4,280 citations
  11. Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014) — 3,967 citations
  12. NeRF: Representing scenes as neural radiance fields for view synthesis — 3,943 citations
  13. Poisson surface reconstruction (2006) — 3,760 citations
  14. Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) — 3,487 citations
  15. Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, Computer Vision and Pattern Recognition) — 3,446 citations
  16. KPConv: Flexible and Deformable Convolution for Point Clouds (2019) — 3,358 citations
  17. Multi-view 3D Object Detection Network for Autonomous Driving (2016) — 3,211 citations
  18. OctoMap: an efficient probabilistic 3D mapping framework based on octrees (2013) — 3,129 citations
  19. Two-Frame Motion Estimation Based on Polynomial Expansion (2003) — 3,116 citations
  20. PointCNN: Convolution On X-Transformed Points (2018) — 2,957 citations
  21. Convolutional Pose Machines (2016) — 2,922 citations
  22. Pixelwise View Selection for Unstructured Multi-View Stereo (2016) — 2,858 citations
  23. KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera (2011) — 2,576 citations
  24. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019) — 2,497 citations
  25. PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization (2015) — 2,475 citations
  26. Screened poisson surface reconstruction (2013) — 2,388 citations
  27. PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes (2017) — 2,347 citations
  28. Efficient RANSAC for Point‐Cloud Shape Detection (2007) — 2,286 citations
  29. Object scene flow for autonomous vehicles (2015) — 2,263 citations
  30. pixelNeRF: Neural Radiance Fields from One or Few Images (2020) — 2,248 citations
  31. End-to-End Recovery of Human Shape and Pose (2017) — 2,097 citations
  32. A Spatio-Temporal Descriptor Based on 3D-Gradients (2008) — 2,054 citations
  33. 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016) — 1,900 citations
  34. AprilTag: A robust and flexible visual fiducial system (2011) — 1,879 citations
  35. Learning Implicit Fields for Generative Shape Modeling (2018) — 1,852 citations
  36. Pyramid Stereo Matching Network (2018) — 1,823 citations
  37. RMPE: Regional Multi-person Pose Estimation (2016) — 1,772 citations
  38. Accurate, Dense, and Robust Multiview Stereopsis (2010) — 1,728 citations
  39. How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks) (2017) — 1,678 citations
  40. MVSNet: Depth Inference for Unstructured Multi-view Stereo (2018) — 1,670 citations
  41. Unique Signatures of Histograms for Local Surface Description (2010) — 1,636 citations
  42. Make3D: Learning 3D Scene Structure from a Single Still Image (2009) — 1,623 citations
  43. OctNet: Learning Deep 3D Representations at High Resolutions (2016) — 1,618 citations
  44. Visual learning and recognition of 3-d objects from appearance (2005) — 1,508 citations
  45. Neural Sparse Voxel Fields (2020) — 1,503 citations
  46. Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (2018) — 1,502 citations
  47. View invariant human action recognition using histograms of 3D joints (2012) — 1,494 citations
  48. Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group (2014) — 1,475 citations
  49. Action recognition based on a bag of 3D points (2010) — 1,474 citations
  50. PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization (2019) — 1,437 citations

Most active researchers

By papers in this topic: a volume measure, not trust.