相关论文: Re-Prompting SAM 3 via Object Retrieval: 3rd of th…
This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios:…
Autonomous-driving perception systems require robust Multi-Object Tracking (MOT) to operate reliably in dynamic environments. MOT maintains consistent object identities across frames while preserving spatial accuracy. Recent foundation…
Video object segmentation (VOS) is a challenging task with wide applications such as video editing and autonomous driving. While Cutie provides strong query-based segmentation and SAM2 offers enriched representations via a pretrained ViT…
The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…
We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars,…
Referring Video Object Segmentation (RVOS) is a challenging task due to its requirement for temporal understanding. Due to the obstacle of computational complexity, many state-of-the-art models are trained on short time intervals. During…
Video Object Segmentation (VOS) aims to track and segment specific objects across entire video sequences, yet it remains highly challenging under complex real-world scenarios. The MOSEv1 and LVOS dataset, adopted in the MOSEv1 challenge on…
In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector. Existing end-to-end methods, MOTR and TrackFormer are inferior to their tracking-by-detection…
Motion Expression guided Video Segmentation is a challenging task that aims at segmenting objects in the video based on natural language expressions with motion descriptions. Unlike the previous referring video object segmentation (RVOS),…
3D multiple object tracking (MOT) plays a crucial role in autonomous driving perception. Recent end-to-end query-based trackers simultaneously detect and track objects, which have shown promising potential for the 3D MOT task. However,…
Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions (referring & reasoning motion expressions) and introducing…
Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…
The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames. Due to the requirement of understanding cross-modal semantics within individual…
We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time. Generalization to new…
In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating…
Referring video object segmentation (RVOS) requires segmenting and tracking objects in videos conditioned on natural-language expressions, demanding fine-grained understanding of both appearance and motion. Building on Sa2VA, which couples…
Referential Video Object Segmentation (RVOS) aims to segment all objects in a video that match a given natural language description, bridging the gap between vision and language understanding. Recent work, such as Sa2VA, combines Large…
Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction. However, the obtained reconstructions also provide useful information for improving tracking. We propose a novel method that…
Event cameras are bio-inspired, motion-activated sensors that demonstrate substantial potential in handling challenging situations, such as motion blur and high-dynamic range. In this paper, we proposed EVI-SAM to tackle the problem of 6…
Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…