Yunhai Tong, Jiangmiao Pang, Kai Chen, Chen Loy, Xiangtai Li, Wenwei Zhang, Guangliang Cheng
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 and KITTI-STEP without bells and whistles. In particular on KITTI-STEP, the simple method can boost almost 12% relative improvements over previous methods. 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% for ResNet50 backbone and 51.5% mAP for Swin-base on YouTube-2019 validation set. We hope this simple yet effective method can serve as a new flexible baseline in video segmentation. 1 * Equal contribution. 1 Both code and models are released at here.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.04656")
get_code_for_paper("2204.04656")
have("2204.04656")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2204.04656.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2204.04656)
Connect an agent — have() is free.