mlsanityData to 7 Oct 2026

NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds

arXiv 2207.09978 ↗First posted 20 Jul 2022cs.CV cs.GRcited by 12

Not on the map. Why?

Abstract (arXiv)

We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

41 of 55 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2017Mask R-CNNcited by 7,259
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  11. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
29 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  3. 2021Neural Fields in Visual Computing and Beyondcited by 539
  4. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  5. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  6. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  7. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  8. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  9. 2019CvxNet: Learnable Convex Decompositioncited by 173
  10. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  11. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  12. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 152
  13. 2019NASA: Neural Articulated Shape Approximationcited by 149
  14. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  15. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  16. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  17. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 98
  18. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  19. 2020An Analysis of SVD for Deep Rotation Estimationcited by 85
  20. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  21. 2021EfficientLPS: Efficient LiDAR Panoptic Segmentationcited by 76
  22. 2020DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolutioncited by 74
  23. 2019Identifying Unknown Instances for Autonomous Drivingcited by 73
  24. 2017Recurrent Pixel Embedding for Instance Groupingcited by 57
  25. 2020Learning Gaussian Instance Segmentation in Point Cloudscited by 33
  26. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  27. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  28. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  29. 2017Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challengecited by 19

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 6; 2025: 2.

12 papers.

  1. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  2. 2023Top-Down Beats Bottom-Up in 3D Instance Segmentationcited by 31
  3. 2024A Unified Framework for 3D Scene Understandingcited by 15
  4. 2023Structured Epipolar Matcher for Local Feature Matchingcited by 8
  5. 2024MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentationcited by 4
  6. 2024CompetitorFormer: Competitor Transformer for 3D Instance Segmentationcited by 4
  7. 2025All in One: Visual-Description-Guided Unified Point Cloud Segmentationcited by 4
  8. 2024ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Methodcited by 2
  9. 2024Joint prototype and coefficient prediction for 3D instance segmentationcited by 1
  10. 2025Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gapcited by 1
  11. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  12. 2024Instance Segmentation of Reinforced Concrete Bridges with Synthetic Point Cloudscited by 0