Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising
solution to enhance zero-shot generalization in dense prediction tasks. However, existing …

In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for
solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection …

Real2Sim2Real plays a critical role in robotic arm control and reinforcement learning, yet
bridging this gap remains a significant challenge due to the complex physical properties of …

Recent developments in monocular depth estimation methods enable high-quality depth
estimation of single-view images but fail to estimate consistent video depth across different …

This study aims to achieve more precise and versatile object control in image-to-video (I2V)
generation. Current methods typically represent the spatial movement of target objects with …

While recent foundational video generators produce visually rich output, they still struggle
with appearance drift, where objects gradually degrade or change inconsistently across …

In this paper, we propose ProTracker, a novel framework for robust and accurate long-term
dense tracking of arbitrary points in videos. The key idea of our method is incorporating …

We propose a simple yet effective approach for few-shot action recognition, emphasizing the
disentanglement of motion and appearance representations. By harnessing recent progress …

Large language model-based (LLM) agents are emerging as a powerful enabler of robust
embodied intelligence due to their capability of planning complex action sequences. Sound …

Current state-of-the-art flow methods are mostly based on dense all-pairs cost volumes.
However, as image resolution increases, the computational and spatial complexity of …