Panoptic Segmentation


Panoptic segmentation is a computer vision task that combines semantic segmentation and instance segmentation to provide a comprehensive understanding of the scene. The goal of panoptic segmentation is to segment the image into semantically meaningful parts or regions, while also detecting and distinguishing individual instances of objects within those regions. In a given image, every pixel is assigned a semantic label, and pixels belonging to things classes (countable objects with instances, like cars and people) are assigned unique instance IDs.

SemRaFiner: Panoptic Segmentation in Sparse and Noisy Radar Point Clouds

Add code
Jul 09, 2025
Viaarxiv icon

PanSt3R: Multi-view Consistent Panoptic Segmentation

Add code
Jun 26, 2025
Viaarxiv icon

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

Add code
Jun 16, 2025
Viaarxiv icon

A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects

Add code
Jun 16, 2025
Viaarxiv icon

SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance

Add code
Jun 12, 2025
Viaarxiv icon

How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation

Add code
May 25, 2025
Viaarxiv icon

ConfLUNet: Multiple sclerosis lesion instance segmentation in presence of confluent lesions

Add code
May 28, 2025
Viaarxiv icon

The Missing Point in Vision Transformers for Universal Image Segmentation

Add code
May 26, 2025
Viaarxiv icon

OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning

Add code
May 22, 2025
Viaarxiv icon

SoftPQ: Robust Instance Segmentation Evaluation via Soft Matching and Tunable Thresholds

Add code
May 17, 2025
Viaarxiv icon