Papers › Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

10 Apr 2022CVPR 2022 1arXiv:2204.04656archive 2025-07-28

Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy

This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable kernels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track "things" and "stuff" in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS, KITTI-STEP, and VIPSeg without bells and whistles. In particular, on KITTI-STEP, the simple method can boost almost 12% relative improvements over previous methods. On VIPSeg, Video K-Net boosts almost 15% relative improvements and results in 39.8 % VPQ. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation, where we obtain 40.5% mAP for ResNet50 backbone and 54.1% mAP for Swin-base on YouTube-2019 validation set. We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design. Both code and models are released at https://github.com/lxtGH/Video-K-Net.

PaperPDFConference PDFCode

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

Code

lxtgh/video-k-net officialmentioned in papermentioned on GitHubpytorchMIT 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationInstance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationVideo Instance SegmentationVideo Panoptic SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation YouTube-VIS validation Video K-Net (Swin-Base) AP50 79.0 #13 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation Video K-Net (Swin-Base) AP75 59.6 #13 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation Video K-Net (Swin-Base) AR1 49.7 #13 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation Video K-Net (Swin-Base) AR10 59.9 #13 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation Video K-Net (Swin-Base) mask AP 54.1 #13 of 44 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS Video K-Net (Swin-B) VPQ 62.2 #3 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS Video K-Net (Swin-B) VPQ (stuff) 71.8 #3 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS Video K-Net (Swin-B) VPQ (thing) 49.8 #3 of 8 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP Video K-Net (Swin-L) AQ 73.0 #1 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP Video K-Net (Swin-L) SQ 75.0 #1 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP Video K-Net (Swin-L) STQ 74.0 #1 of 6 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

K-Net

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