Papers › Scene-Centric Unsupervised Panoptic Segmentation

Scene-Centric Unsupervised Panoptic Segmentation

2 Apr 2025CVPR 2025 1arXiv:2504.01955archive 2025-07-28

Oliver Hahn, Christoph Reich, Nikita Araslanov, Daniel Cremers, Christian Rupprecht, Stefan Roth

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data, combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4% points in PQ.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2504.01955")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: official repository: 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

visinf/cups officialmentioned in papermentioned on GitHubpytorchApache-2.0 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.

Code Syntology ran Syntology

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 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 visinf/cups. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

denormalize visinf/cups/cups/utils.py official repository unverified Apache-2.0 (permissive) · 60c827a00b5a152a · report
get_default_config visinf/cups/cups/config.py official repository unverified Apache-2.0 (permissive) · 42ac537df132d369 · report
get_label_efficient_augmentations visinf/cups/cups/augmentation.py official repository unverified Apache-2.0 (permissive) · 413101e146fc43f2 · report
get_pseudo_label_augmentations visinf/cups/cups/augmentation.py official repository unverified Apache-2.0 (permissive) · 08b8b7e673e8f446 · report
normalize visinf/cups/cups/utils.py official repository unverified Apache-2.0 (permissive) · c9001204e49aa348 · report
normalize_min_max_m1_1 visinf/cups/cups/utils.py official repository unverified Apache-2.0 (permissive) · 2d2fde55e9fd49fe · report
prediction_to_standard_format visinf/cups/cups/model/model.py official repository unverified Apache-2.0 (permissive) · abf1bf4d18504b03 · report
soft_hamming_distance visinf/cups/cups/scene_flow_2_se3/loss.py official repository unverified Apache-2.0 (permissive) · af00744bd55b9c34 · report

Tasks

Instance SegmentationPanoptic SegmentationPseudo LabelScene UnderstandingSegmentationSemantic SegmentationUnsupervised Object DetectionUnsupervised Panoptic SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Panoptic Segmentation BDD100K val CUPS (40 pseudo-classes) PQ 21.9 #1 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation BDD100K val CUPS (54 pseudo-classes) PQ 21.8 #2 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation BDD100K val CUPS (27 pseudo-classes) PQ 19.9 #3 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation Cityscapes CUPS (54 pseudo-classes) PQ 30.6 #1 of 5 Archive leaderboard report
Unsupervised Panoptic Segmentation Cityscapes CUPS (40 pseudo-classes) PQ 30.3 #2 of 5 Archive leaderboard report
Unsupervised Panoptic Segmentation Cityscapes CUPS (27 pseudo-classes) PQ 27.8 #3 of 5 Archive leaderboard report
Unsupervised Panoptic Segmentation KITTI CUPS (54 pseudo-classes) PQ 28.5 #1 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation KITTI CUPS (40 pseudo-classes) PQ 28.1 #2 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation KITTI CUPS (27 pseudo-classes) PQ 25.5 #3 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation MUSES: MUlti-SEnsor Semantic perception dataset CUPS (40 pseudo-classes) PQ 28.2 #1 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation MUSES: MUlti-SEnsor Semantic perception dataset CUPS (27 pseudo-classes) PQ 24.4 #2 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation MUSES: MUlti-SEnsor Semantic perception dataset CUPS (54 pseudo-classes) PQ 22.8 #3 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation Waymo Open Dataset CUPS (54 pseudo-classes) PQ 27.3 #1 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation Waymo Open Dataset CUPS (40 pseudo-classes) PQ 27.2 #2 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation Waymo Open Dataset CUPS (27 pseudo-classes) PQ 26.4 #3 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test CUPS Accuracy 83.2 #1 of 14 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test CUPS mIoU 26.8 #1 of 14 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.

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