{"url":"/method/pointrend","slug":"pointrend","name":"PointRend","full_name":"PointRend","full_name_withheld":false,"description_markdown":"**PointRend** is a module for image segmentation tasks, such as instance and semantic segmentation, that attempts to treat segmentation as image rending problem to efficiently \"render\" high-quality label maps. It uses a subdivision strategy to adaptively select a non-uniform set of points at which to compute labels. PointRend can be incorporated into popular meta-architectures for both instance segmentation (e.g. [Mask R-CNN](https://paperswithcode.com/method/mask-r-cnn)) and semantic segmentation (e.g. [FCN](https://paperswithcode.com/method/fcn)). Its subdivision strategy efficiently computes high-resolution segmentation maps using an order of magnitude fewer floating-point operations than direct, dense computation.\r\n\r\nPointRend is a general module that admits many possible implementations. Viewed abstractly, a PointRend module accepts one or more typical CNN feature maps $f\\left(x\\_{i}, y\\_{i}\\right)$ that are defined over regular grids, and outputs high-resolution predictions $p\\left(x^{'}\\_{i}, y^{'}\\_{i}\\right)$ over a finer grid. Instead of making excessive predictions over all points on the output grid, PointRend makes predictions only on carefully selected points. To make these predictions, it extracts a point-wise feature representation for the selected points by interpolating $f$, and uses a small point head subnetwork to predict output labels from the point-wise features.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1912.08193v2","title":"PointRend: Image Segmentation as Rendering","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Modules","url":"/methods/category/semantic-segmentation-modules","pwc_aliases":[]}],"n_papers_tagged":9,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/effseg-efficient-fine-grained-instance","title":"EffSeg: Efficient Fine-Grained Instance Segmentation using Structure-Preserving Sparsity","date":"2023-07-04","arxiv_id":"2307.01545","n_code_links":1,"syntology":null},{"paper":"/paper/mars-mask-attention-refinement-with","title":"MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation","date":"2023-05-01","arxiv_id":"2305.04743","n_code_links":1,"syntology":null},{"paper":null,"title":"ALiSNet: Accurate and Lightweight Human Segmentation Network for Fashion E-Commerce","date":"2023-04-15","arxiv_id":"2304.07533","n_code_links":0,"syntology":null},{"paper":null,"title":"SEMI-PointRend: Improved Semiconductor Wafer Defect Classification and Segmentation as Rendering","date":"2023-02-19","arxiv_id":"2302.09569","n_code_links":0,"syntology":null},{"paper":"/paper/boundarysqueeze-image-segmentation-as","title":"BoundarySqueeze: Image Segmentation as Boundary Squeezing","date":"2021-05-25","arxiv_id":"2105.11668","n_code_links":1,"syntology":null},{"paper":"/paper/pointly-supervised-instance-segmentation","title":"Pointly-Supervised Instance Segmentation","date":"2021-04-13","arxiv_id":"2104.06404","n_code_links":3,"syntology":null},{"paper":null,"title":"2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020","date":"2020-10-21","arxiv_id":"2010.10957","n_code_links":0,"syntology":null},{"paper":"/paper/towards-fine-grained-large-object","title":"Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track","date":"2020-09-10","arxiv_id":"2009.04650","n_code_links":1,"syntology":null},{"paper":"/paper/pointrend-image-segmentation-as-rendering","title":"PointRend: Image Segmentation as Rendering","date":"2019-12-17","arxiv_id":"1912.08193","n_code_links":14,"syntology":{"ran":5,"of":18,"unverified":13,"pointer_only":0}}],"papers_shown":9,"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":8},{"task":"/task/segmentation","name":"Segmentation","papers":8},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":8},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":3},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/virtual-try-on","name":"Virtual Try-on","papers":1},{"task":"/task/weakly-supervised-instance-segmentation","name":"Weakly-supervised instance segmentation","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":2},{"year":"2021","papers":2},{"year":"2023","papers":4}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pointrend"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}