Related papers: TRec: Learning Hand-Object Interactions through 2D…
To track the 3D locations and trajectories of the other traffic participants at any given time, modern autonomous vehicles are equipped with multiple cameras that cover the vehicle's full surroundings. Yet, camera-based 3D object tracking…
Multi-object tracking (MOT) is a core task in computer vision that involves detecting objects in video frames and associating them across time. The rise of deep learning has significantly advanced MOT, particularly within the…
Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In…
Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited…
We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D…
Multi-object tracking from RGB-D video sequences is a challenging problem due to the combination of changing viewpoints, motion, and occlusions over time. We observe that having the complete geometry of objects aids in their tracking, and…
Real-time robotic grasping, supporting a subsequent precise object-in-hand operation task, is a priority target towards highly advanced autonomous systems. However, such an algorithm which can perform sufficiently-accurate grasping with…
This paper presents the outcomes of a contest organized to evaluate methods for the online recognition of heterogeneous gestures from sequences of 3D hand poses. The task is the detection of gestures belonging to a dictionary of 16 classes…
This paper presents a novel real-time tracking system capable of improving body pose estimation algorithms in distributed camera networks. The first stage of our approach introduces a linear Kalman filter operating at the body joints level,…
The accurate tracking of live cells using video microscopy recordings remains a challenging task for popular state-of-the-art image processing based object tracking methods. In recent years, several existing and new applications have…
Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…
Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs…
Direct methods have shown excellent performance in the applications of visual odometry and SLAM. In this work we propose to leverage their effectiveness for the task of 3D multi-object tracking. To this end, we propose DirectTracker, a…
To catch a thrown object, a robot must be able to perceive the object's motion and generate control actions in a timely manner. Rather than explicitly estimating the object's 3D position, this work focuses on a novel approach that…
Recent approaches for 3D object detection have made tremendous progresses due to the development of deep learning. However, previous researches are mostly based on individual frames, leading to limited exploitation of information between…
We present a novel approach to place recognition well-suited to environments with many dynamic objects--objects that may or may not be present in an agent's subsequent visits. By incorporating an object-detecting preprocessing step, our…
A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond…
We study object motion path editing in videos, where the goal is to alter a target object's trajectory while preserving the original scene content. Unlike prior video editing methods that primarily manipulate appearance or rely on…
3D single object tracking with point clouds is a critical task in 3D computer vision. Previous methods usually input the last two frames and use the predicted box to get the template point cloud in previous frame and the search area point…
We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook:…