相关论文: Inferring Dynamic Physical Properties from Video F…

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…

Motion blur in videos captured by autonomous vehicles and robots can degrade their perception capability. In this work, we present a novel approach to video deblurring by fitting a deep network to the test video. Our key observation is that…

We consider the problem of a robot learning the mechanical properties of objects through physical interaction with the object, and introduce a practical, data-efficient approach for identifying the motion models of these objects. The…

Static appearance of video may impede the ability of a deep neural network to learn motion-relevant features in video action recognition. In this paper, we introduce a new concept, Dynamic Appearance (DA), summarizing the appearance…

Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to…

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…

In monocular videos that capture dynamic scenes, estimating the 3D geometry of video contents has been a fundamental challenge in computer vision. Specifically, the task is significantly challenged by the object motion, where existing…

Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent…

Humans perceive the world by interacting with objects, which often happens in a dynamic way. For example, a human would shake a bottle to guess its content. However, it remains a challenge for robots to understand many dynamic signals…

We consider the problem of estimating frame-level full human body meshes given a video of a person with natural motion dynamics. While much progress in this field has been in single image-based mesh estimation, there has been a recent…

We develop a method for learning periodic tasks from visual demonstrations. The core idea is to leverage periodicity in the policy structure to model periodic aspects of the tasks. We use active learning to optimize parameters of rhythmic…

Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and…

Videos often capture objects, their visible properties, their motion, and the interactions between different objects. Objects also have physical properties such as mass, which the imaging pipeline is unable to directly capture. However,…

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vision Language Models (VLMs), have demonstrated remarkable…

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual worlds. In this work, we focus on predicting the dynamics…

Estimating the pose of a moving camera from monocular video is a challenging problem, especially due to the presence of moving objects in dynamic environments, where the performance of existing camera pose estimation methods are susceptible…

This paper presents a shape-theoretic framework for dynamical analysis of nonlinear dynamical systems which appear frequently in several video-based inference tasks. Traditional approaches to dynamical modeling have included linear and…

In this paper we address the problem of tracking non-rigid objects whose local appearance and motion changes as a function of time. This class of objects includes dynamic textures such as steam, fire, smoke, water, etc., as well as…

The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame. However, a direct…