Papers › PointRend: Image Segmentation as Rendering

PointRend: Image Segmentation as Rendering

17 Dec 2019CVPR 2020 6arXiv:1912.08193archive 2025-07-28

Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (facebookresearch/detectron2) is linked to this paper; the 18 samples below come from 3 community repositories. Syntology harvested code from facebookresearch/detectron2 for 2 other papers.

facebookresearch/detectron2: Syntology's graph links these samples to Focal Loss for Dense Object Detection (arXiv:1708.02002; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified) and An Extendable, Efficient and Effective Transformer-based Object Detector (arXiv:2204.07962; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 18 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 3 repositories, 16 ran (11 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

14 repositories listed; official and paper-mentioned ones first.

facebookresearch/detectron2 officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Focal Loss for Dense Object Detection (arXiv:1708.02002; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified) and An Extendable, Efficient and Effective Transformer-based Object Detector (arXiv:2204.07962; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
2020-sk49/VFOST mentioned on GitHubpytorchSyntology: not harvested report
CuberrChen/PointRend-Paddle mentioned on GitHubpaddleApache-2.0Syntology: 8 samples, 8 ran (2 instrument-failed) · 0 unverified report
JamesQFreeman/PointRend mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ayoolaolafenwa/PixelLib mentioned on GitHubtfMITSyntology: 9 samples, 7 ran (2 instrument-failed) · 2 unverified report
elliottwu/sorderender mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to De-rendering the World's Revolutionary Artefacts (arXiv:2104.03954; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
hhhhnwl/PointRend-simple-pytorch mentioned on GitHubpytorchSyntology: not harvested report
kmswlee/ainized-PointRend mentioned on GitHubSyntology: not harvested report
saehan-choi/pixellib_auto_labelling mentioned on GitHubpytorchMITSyntology: not harvested report
zsef123/PointRend-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-222 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmsegmentation pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Perceptual Artifacts Localization for Image Synthesis Tasks (arXiv:2310.05590; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
11ran
2unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

CuberrChen/PointRend-Paddle community (archive-listed) 8 samples, 8 ran (2 instrument-failed) · 0 unverified
flip_combination in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · 95bccf5957a196e4 · report fixture: signature flip_horizontal:bool/0/bool, flip_vertical:bool/0/bool · returned list · level recorded 2026-09-24
get_color_map_list utils/gray2pseudo_color.py ran fingerprinted Apache-2.0 (permissive) · 4a169e8f6527333b · report fixture: signature num_classes:int/0/int · returned list · level recorded 2026-09-24
get_files in 30 papers utils/create_dataset_list.py ran Apache-2.0 (permissive) · 10c053391f452886 · report fixture: signature image_or_label:str/0/str, dataset_split:str/0/str, args:Args/0/? · returned list · level recorded 2026-09-24
get_image_list in 15 papers predict.py ran Apache-2.0 (permissive) · c8f710d7401e0006 · report fixture: signature image_path:str/0/str · returned tuple · level recorded 2026-09-24
get_reverse_list in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · 026fee631ce4a66c · report fixture: signature ori_shape:list/1/int, transforms:list/1/Resize · returned list · level recorded 2026-09-24
get_test_config in 9 papers val.py ran · our draft was wrong Apache-2.0 (permissive) · 20eb3e6b0aba73e4 · report fixture: signature cfg:SimpleConfig/0/?, args:SimpleArgs/0/? · returned dict · level recorded 2026-09-22
get_test_config in 9 papers predict.py ran Apache-2.0 (permissive) · 32d2a7cc8725e25e · report fixture: signature cfg:Config/0/?, args:Args/0/? · returned dict · level recorded 2026-09-24
partition_list in 10 papers paddleseg/core/predict.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report fixture: signature arr:list/1/int, m:int/0/int · returned list · level recorded 2026-09-22
JamesQFreeman/PointRend community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
getpoint pointGenerate.py ran · our draft was wrong fingerprinted MIT (permissive) · 1fe9d10d9e769de8 · report fixture: signature mask_img:ndarray/2/float, k:int/0/int, beta:float/0/float, training:bool/0/bool, nearest_neighbor:int/0/int, new_if_near:bool/0/bool · returned list · level recorded 2026-09-22
ayoolaolafenwa/PixelLib community (archive-listed) 9 samples, 7 ran (2 instrument-failed) · 2 unverified
compute_backbone_shapes in 12 papers pixellib/instance/mask_rcnn.py ran MIT (permissive) · 18ea12b2eeecd592 · report fixture: signature config:Config/0/?, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-24
compute_iou in 68 papers pixellib/instance/utils.py ran MIT (permissive) · 64403fb78c59e685 · report fixture: signature box:ndarray/1/float, boxes:ndarray/2/float, box_area:float/0/float, boxes_area:ndarray/1/float · returned ndarray · level recorded 2026-09-24
compute_overlaps in 11 papers pixellib/instance/utils.py ran fingerprinted MIT (permissive) · 8ee1bf912c0d3692 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
conv_block in 95 papers pixellib/instance/mask_rcnn.py ran MIT (permissive) · 0c9b8c863cf414f7 · report fixture: signature input_tensor:KerasTensor/4/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, strides:tuple/1/int, use_bias:bool/0/bool, train_bn:bool/0/bool · returned KerasTensor · level recorded 2026-09-24
convert_basic_c2_names in 46 papers pixellib/torchbackend/instance/checkpoint/c2_model_loading.py ran · our draft was wrong MIT (permissive) · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers pixellib/torchbackend/instance/checkpoint/c2_model_loading.py ran · our draft was wrong MIT (permissive) · e36f87059208bb7e · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
extract_bboxes in 14 papers pixellib/instance/utils.py ran fingerprinted MIT (permissive) · 75499b9fb42b31f7 · report fixture: signature mask:ndarray/3/int · returned ndarray · level recorded 2026-09-24
align_and_update_state_dicts in 21 papers pixellib/torchbackend/instance/checkpoint/c2_model_loading.py unverified MIT (permissive) · ac2638463572c152 · report
identity_block in 32 papers pixellib/instance/mask_rcnn.py unverified MIT (permissive) · 4ea5e920502e7ce7 · report

Tasks

Image SegmentationInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO 2017 val PointRend (MaskR-CNN, ResNet-50-FPN) mask AP* 39.7 #3 of 4 Archive leaderboard report
Instance Segmentation Cityscapes val PointRend mask AP 35.8 #17 of 17 Archive leaderboard report
Semantic Segmentation Cityscapes val SemanticFPN P2-P5 + PointRend mIoU 78.6 #60 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionASPPBatch NormalizationConvolutionDeepLabv3Dense ConnectionsDilated ConvolutionFPNFeedforward NetworkGroup NormalizationLinear WarmupMask R-CNNPanoptic FPNPointRendRPNRandom Horizontal FlipRandom ScalingReLURoIAlignSGD with MomentumSigmoid ActivationSoftmaxSpatial Pyramid PoolingWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections