mlsanityData to 7 Oct 2026

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

arXiv 2003.05855 ↗First posted 12 Mar 2020cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 13; 2023: 11; 2024: 4; 2025: 5; 2026: 2.

47 papers.

Sort:

By area:

  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  3. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  4. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  5. 2023CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognitioncited by 77
  6. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  7. 2023Deep Learning on Implicit Neural Representations of Shapescited by 62
  8. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  9. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  10. 2022Approximate Differentiable Rendering with Algebraic Surfacescited by 44
  11. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 41
  12. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
35 more
  1. 2021Bootstrap Your Own Correspondencescited by 27
  2. 2023DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classificationcited by 23
  3. 2022Rethinking the compositionality of point clouds through regularization in the hyperbolic spacecited by 18
  4. 2022E2PN: Efficient SE(3)-Equivariant Point Networkcited by 17
  5. 2022SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondencecited by 13
  6. 2023JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fieldscited by 13
  7. 2021IMFNet: Interpretable Multimodal Fusion for Point Cloud Registrationcited by 12
  8. 2024GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understandingcited by 12
  9. 20213D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learningcited by 11
  10. 2022LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsamplingcited by 8
  11. 2021WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registrationcited by 7
  12. 2023Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentationcited by 7
  13. 2023Generalizable Local Feature Pre-training for Deformable Shape Analysiscited by 6
  14. 2022Projection-based Point Convolution for Efficient Point Cloud Segmentationcited by 4
  15. 2022Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervisioncited by 4
  16. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  17. 2022Learning a Task-specific Descriptor for Robust Matching of 3D Point Cloudscited by 3
  18. 2023Weakly Supervised 3D Instance Segmentation without Instance-level Annotationscited by 3
  19. 2025Efficient Spiking Point Mamba for Point Cloud Analysiscited by 3
  20. 2021FC2T2: The Fast Continuous Convolutional Taylor Transform with Applications in Vision and Graphicscited by 2
  21. 2023SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registrationcited by 2
  22. 2024Optimizing 3D Geometry Reconstruction from Implicit Neural Representationscited by 2
  23. 2025CanonNet: Canonical Ordering and Curvature Learning for Point Cloud Analysiscited by 2
  24. 2026RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformercited by 2
  25. 2021Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Datacited by 1
  26. 2022SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancementcited by 1
  27. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  28. 2025Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classificationcited by 1
  29. 2022Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Setscited by 0
  30. 2022Learning task-specific features for 3D pointcloud graph creationcited by 0
  31. 2023BluNF: Blueprint Neural Fieldcited by 0
  32. 2024NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuningcited by 0
  33. 2025Geometry-Aware 3D Salient Object Detection Networkcited by 0
  34. 2025SANDRO: a Robust Solver with a Splitting Strategy for Point Cloud Registrationcited by 0
  35. 2026CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labelscited by 0