Papers › NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation

NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation

29 Aug 2023arXiv:2308.15266archive 2025-07-28

Tim Meinhardt, Matt Feiszli, Yuchen Fan, Laura Leal-Taixe, Rakesh Ranjan

Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing. However, the recent success of online methods questions this belief, in particular, for challenging and long video sequences. We understand this work as a rebuttal of those recent observations and an appeal to the community to focus on dedicated near-online VIS approaches. To support our argument, we present a detailed analysis on different processing paradigms and the new end-to-end trainable NOVIS (Near-Online Video Instance Segmentation) method. Our transformer-based model directly predicts spatio-temporal mask volumes for clips of frames and performs instance tracking between clips via overlap embeddings. NOVIS represents the first near-online VIS approach which avoids any handcrafted tracking heuristics. We outperform all existing VIS methods by large margins and provide new state-of-the-art results on both YouTube-VIS (2019/2021) and the OVIS benchmarks.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Instance SegmentationSegmentationSemantic SegmentationVideo Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation OVIS validation NOVIS (Swin-L) AP50 68.3 #13 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (Swin-L) AP75 43.8 #13 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (Swin-L) AR1 19.4 #13 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (Swin-L) AR10 46.9 #13 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (Swin-L) mask AP 43.5 #13 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (ResNet-50) AP50 56.2 #28 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (ResNet-50) AP75 32.6 #28 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (ResNet-50) AR1 15.7 #28 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (ResNet-50) AR10 37.1 #28 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation NOVIS (ResNet-50) mask AP 32.7 #28 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (Swin-L) AP50 82.0 #10 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (Swin-L) AP75 66.5 #10 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (Swin-L) AR1 47.9 #10 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (Swin-L) AR10 64.4 #10 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (Swin-L) mask AP 59.8 #10 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (ResNet-50) AP50 69.4 #23 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (ResNet-50) AP75 50.0 #23 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (ResNet-50) AR1 41.3 #23 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (ResNet-50) AR10 54.4 #23 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 NOVIS (ResNet-50) mask AP 47.2 #23 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation NOVIS (ResNet-50) AP50 75.7 #14 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation NOVIS (ResNet-50) AP75 56.9 #14 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation NOVIS (ResNet-50) AR1 50.3 #14 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation NOVIS (ResNet-50) AR10 60.6 #14 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation NOVIS (ResNet-50) mask AP 52.8 #14 of 44 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

Focus

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