mlsanityData to 7 Oct 2026

PointRend: Image Segmentation as Rendering

arXiv 1912.08193 ↗First posted 17 Dec 2019cs.CVcited by 439

Not on the map. Why?

Abstract (arXiv)

We present a new method for efficient high-quality image segmentation of objects and scenes. By analogizing classical computer graphics methods for efficient rendering with over- and undersampling challenges faced in pixel labeling tasks, we develop a unique perspective of image segmentation as a rendering problem. From this vantage, we present the PointRend (Point-based Rendering) neural network module: a module that performs point-based segmentation predictions at adaptively selected locations based on an iterative subdivision algorithm. PointRend can be flexibly applied to both instance and semantic segmentation tasks by building on top of existing state-of-the-art models. While many concrete implementations of the general idea are possible, we show that a simple design already achieves excellent results. Qualitatively, PointRend outputs crisp object boundaries in regions that are over-smoothed by previous methods. Quantitatively, PointRend yields significant gains on COCO and Cityscapes, for both instance and semantic segmentation. PointRend's efficiency enables output resolutions that are otherwise impractical in terms of memory or computation compared to existing approaches. Code has been made available at https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend.

Key facts. Cited by 439 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 107; 2022: 88; 2023: 107; 2024: 60; 2025: 34; 2026: 43.

439 papers.

Sort:

By area:

  1. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  2. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  3. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  5. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  6. 2021Dynamic Neural Networks: A Surveycited by 405
  7. 2023Segment Anything in High Qualitycited by 373
  8. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  9. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  10. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  11. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  12. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
38 more
  1. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  2. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  3. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  4. 2023Putting the Object Back into Video Object Segmentationcited by 182
  5. 2023RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Modelcited by 180
  6. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  7. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  8. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  9. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 139
  10. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 136
  11. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  12. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  13. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  14. 2021Salient Object Detection via Integrity Learningcited by 133
  15. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  16. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  17. 2023Drivable 3D Gaussian Avatarscited by 120
  18. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  19. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  20. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
  21. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
  22. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  23. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  24. 2021Locate then Segment: A Strong Pipeline for Referring Image Segmentationcited by 98
  25. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  26. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  27. 2024DINO-X: A Unified Vision Model for Open-World Object Detection and Understandingcited by 85
  28. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  29. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  30. 2021Pointly-Supervised Instance Segmentationcited by 83
  31. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  32. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  33. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  34. 2022Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applicationscited by 78
  35. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  36. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  37. 2023Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clipscited by 73
  38. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71

50 most cited of 439 All 439 (JSON)