相关论文: TAPIR: Tracking Any Point with per-frame Initializ…

Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video, even in the presence of occlusions. Traditional methods use optical flow models to…

The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching…

Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos,…

Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking,…

Capture stages are high-end sources of state-of-the-art recordings for downstream applications in movies, games, and other media. One crucial step in almost all pipelines is matting, i.e., separating captured performances from the…

Robot person following (RPF) is a core capability in human-robot interaction, enabling robots to assist users in daily activities, collaborative work, and other service scenarios. However, achieving practical RPF remains challenging due to…

We present the first real-time human performance capture approach that reconstructs dense, space-time coherent deforming geometry of entire humans in general everyday clothing from just a single RGB video. We propose a novel two-stage…

We propose a novel part-based method for tracking an arbitrary object in challenging video sequences. The colour distribution of tracked image patches on the target object are represented by pairs of RGB samples and counts of how many…

Video Instance Segmentation is a fundamental computer vision task that deals with segmenting and tracking object instances across a video sequence. Most existing methods typically accomplish this task by employing a multi-stage top-down…

We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT…

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mounted displays…

Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge…

Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for…

We study informative path planning (IPP) with travel budgets in cluttered environments, where an agent collects measurements of a latent field modeled as a Gaussian process (GP) to reduce uncertainty at target locations. Graph-based solvers…

Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…

Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in…

This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video. Additionally, SAM-Track employs multimodal interaction methods that enable…

Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of…

Quantitative tracking of features from video images is a basic technique employed in many areas of science. Here, we present a method for the tracking of features that partially overlap, in order to be able to track so-called colloidal…