Pith. sign in

REVIEW 1 cited by

PanSR: An Object-Centric Mask Transformer for Panoptic Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.10589 v1 pith:TIVYJZOX submitted 2024-12-13 cs.CV

PanSR: An Object-Centric Mask Transformer for Panoptic Segmentation

classification cs.CV
keywords objectspansrpanopticperformancescenessegmentationcrowdedfundamental
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Panoptic segmentation is a fundamental task in computer vision and a crucial component for perception in autonomous vehicles. Recent mask-transformer-based methods achieve impressive performance on standard benchmarks but face significant challenges with small objects, crowded scenes and scenes exhibiting a wide range of object scales. We identify several fundamental shortcomings of the current approaches: (i) the query proposal generation process is biased towards larger objects, resulting in missed smaller objects, (ii) initially well-localized queries may drift to other objects, resulting in missed detections, (iii) spatially well-separated instances may be merged into a single mask causing inconsistent and false scene interpretations. To address these issues, we rethink the individual components of the network and its supervision, and propose a novel method for panoptic segmentation PanSR. PanSR effectively mitigates instance merging, enhances small-object detection and increases performance in crowded scenes, delivering a notable +3.4 PQ improvement over state-of-the-art on the challenging LaRS benchmark, while reaching state-of-the-art performance on Cityscapes. The code and models will be publicly available at https://github.com/lojzezust/PanSR.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. 4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview

    cs.CV 2026-04 unverdicted novelty 2.0

    The report overviews five maritime computer vision benchmark challenges, their datasets, protocols, quantitative results, and top team approaches from the MaCVi 2026 workshop.