NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
This work addresses video instance segmentation for computer vision applications, offering a novel near-online approach that is not incremental but represents a rebuttal to recent trends.
The authors tackled the problem of video instance segmentation by challenging the belief that offline methods are superior, presenting NOVIS, a near-online method that outperforms all existing approaches with large margins, achieving state-of-the-art results on YouTube-VIS and OVIS benchmarks.
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.