PVUW: Pixel-level Video Understanding in the Wild Challenge

Introduction

The 4th PVUW challenge will be held in conjunction with CVPR 2025 at the Music City Center, Nashville TN. Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Since the real-world is actually video-based rather than a static state, learning to perform video segmentation is more reasonable and practical for realistic applications. To advance the segmentation task from images to videos, we will present new datasets and competitions in this workshop, aiming at performing the challenging yet practical Pixel-level Video Understanding in the Wild (PVUW). This workshop includes workshop papers:

Semantic/panoptic segmentation for images/videos

Referring image/video comprehension/segmentation

Video object/instance segmentation

Video understanding in complex environments

Language-guided video understanding

Audio-guided video segmentation

Efficient computation for video scene parsing

Semi-supervised recognition in videos

New metrics to evaluate the quality of video scene parsing results

Real-world video applications, e.g., autonomous driving, indoor robotics, visual navigation, etc.

Dates

Event	Date
Challenge release	TBD
Validation server online	TBD
Test server online	TBD
Submission deadline	TBD
Notification	TBD

Speakers

Xiangtai Li

ByteDance

Hengshuang Zhao

The University of Hong Kong

Tracks & Submission

Track 1: Complex Video Object Segmentation (MOSE) Track

The complex video object segmentation task aims to track and segment objects in complex environments.

Track 2: Motion Expression guided Video Segmentation (MeViS) Track

The motion expression guided video segmentation track focuses on segmenting objects in video content based on a sentence describing the motion of the objects.