Related papers: PoseTraj: Pose-Aware Trajectory Control in Video D…

We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all…

We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from sparse image points on the objects to be tracked, our approach tracks multiple unseen objects…

Talking head generation is to generate video based on a given source identity and target motion. However, current methods face several challenges that limit the quality and controllability of the generated videos. First, the generated face…

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and…

Modeling trajectory data with generic-purpose dense representations has become a prevalent paradigm for various downstream applications, such as trajectory classification, travel time estimation and similarity computation. However, existing…

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly,…

We introduce ForeSight, a novel joint detection and forecasting framework for vision-based 3D perception in autonomous vehicles. Traditional approaches treat detection and forecasting as separate sequential tasks, limiting their ability to…

Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background…

Accurate 6D pose estimation is key for robotic manipulation, enabling precise object localization for tasks like grasping. We present RAG-6DPose, a retrieval-augmented approach that leverages 3D CAD models as a knowledge base by integrating…

In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated…

Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…

We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of…

We address the problem of action-conditioned generation of human motion sequences. Existing work falls into two categories: forecast models conditioned on observed past motions, or generative models conditioned on action labels and duration…

6D pose estimation is the task of predicting the translation and orientation of objects in a given input image, which is a crucial prerequisite for many robotics and augmented reality applications. Lately, the Transformer Network…

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…

Creating believable motions for various characters has long been a goal in computer graphics. Current learning-based motion synthesis methods depend on extensive motion datasets, which are often challenging, if not impossible, to obtain. On…

Visual pose tracking is playing an increasingly vital role in industrial contexts in recent years. However, the pose tracking for industrial metal objects remains a challenging task especially in the real world-environments, due to the…

We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints. Beyond generating the heatmap of a joint in a given frame, our system also learns to predict the offset of the joint from a…

Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still exist two problems to be further solved. First, existing…

Object pose tracking is one of the pivotal technologies in multimedia, attracting ever-growing attention in recent years. Existing methods employing traditional cameras encounter numerous challenges such as motion blur, sensor noise,…