Related papers: Generative Point Tracking with Flow Matching

Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this…

Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an…

The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative…

Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects…

Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches…

3D multi-object tracking and trajectory prediction are two crucial modules in autonomous driving systems. Generally, the two tasks are handled separately in traditional paradigms and a few methods have started to explore modeling these two…

Point tracking models often struggle to generalize to real-world videos because large-scale training data is predominantly synthetic$\unicode{x2014}$the only source currently feasible to produce at scale. Collecting real-world annotations,…

Joint pedestrian trajectory prediction has long grappled with the inherent unpredictability of human behaviors. Recent investigations employing variants of conditional diffusion models in trajectory prediction have exhibited notable…

With the rapid advancement of diffusion-based generative models, portrait image animation has achieved remarkable results. However, it still faces challenges in temporally consistent video generation and fast sampling due to its iterative…

Panoramic video generation aims to synthesize 360-degree immersive videos, holding significant importance in the fields of VR, world models, and spatial intelligence. Existing works fail to synthesize high-quality panoramic videos due to…

Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…

This paper proposes a concise, elegant, and robust pipeline to estimate smooth camera trajectories and obtain dense point clouds for casual videos in the wild. Traditional frameworks, such as ParticleSfM~\cite{zhao2022particlesfm}, address…

Visual odometry estimates the motion of a moving camera based on visual input. Existing methods, mostly focusing on two-view point tracking, often ignore the rich temporal context in the image sequence, thereby overlooking the global motion…

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…

Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We consider an occluded point to be one that is imaged in the first frame but not in the next, a slight overloading of the standard definition…

3D multi-object tracking (MOT) and trajectory forecasting are two critical components in modern 3D perception systems. We hypothesize that it is beneficial to unify both tasks under one framework to learn a shared feature representation of…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduced TAPNext approach proposes an end-to-end, recurrent transformer architecture to track…

Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive…

Vision-language tracking has gained increasing attention in many scenarios. This task simultaneously deals with visual and linguistic information to localize objects in videos. Despite its growing utility, the development of vision-language…