Sam 2: Segment anything in images and videos
We present Segment Anything Model 2 (SAM 2), a foundation model towards solving
promptable visual segmentation in images and videos. We build a data engine, which …
promptable visual segmentation in images and videos. We build a data engine, which …
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Despite the promising performance of current video segmentation models on existing
benchmarks, these models still struggle with complex scenes. In this paper, we introduce the …
benchmarks, these models still struggle with complex scenes. In this paper, we introduce the …
1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many
new challenges to the field of referring video object segmentation (RVOS). In this technical …
new challenges to the field of referring video object segmentation (RVOS). In this technical …
CSS-Segment: 2nd Place Report of LSVOS Challenge VOS Track
J Chai, Q Ma, J Zhang, L Jiao, F Liu - arXiv preprint arXiv:2408.13582, 2024 - arxiv.org
Video object segmentation is a challenging task that serves as the cornerstone of numerous
downstream applications, including video editing and autonomous driving. In this technical …
downstream applications, including video editing and autonomous driving. In this technical …
LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS
X Liu, J Zhang, K Zhang, X Liu, L Li - arXiv preprint arXiv:2408.10469, 2024 - arxiv.org
Video Object Segmentation (VOS) presents several challenges, including object occlusion
and fragmentation, the dis-appearance and re-appearance of objects, and tracking specific …
and fragmentation, the dis-appearance and re-appearance of objects, and tracking specific …