Related papers: EpO-Net: Exploiting Geometric Constraints on Dense…

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture…

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting…

With the rapid development of deep learning, video deraining has experienced significant progress. However, existing video deraining pipelines cannot achieve satisfying performance for scenes with rain layers of complex spatio-temporal…

Inspired by the complementarity between conventional frame-based and bio-inspired event-based cameras, we propose a multi-modal based approach to fuse visual cues from the frame- and event-domain to enhance the single object tracking…

Background modeling and subtraction is a promising research area with a variety of applications for video surveillance. Recent years have witnessed a proliferation of effective learning-based deep neural networks in this area. However, the…

We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints. A neural projection operator lies at the heart of our approach, composed of a lightweight network with an…

Object detection has long been a topic of high interest in computer vision literature. Motivated by the fact that annotating data for the multi-object tracking (MOT) problem is immensely expensive, recent studies have turned their attention…

Deep learning has shown strong potential for scientific discovery, but its ability to model macroscopic rigid-body kinematic constraints remains underexplored. We study this problem on spatial over-constrained mechanisms and propose…

Geometric deep learning has recently gained significant attention in the computer vision community for its ability to capture meaningful representations of data lying in a non-Euclidean space. To this end, we propose E2E-GNet, an end-to-end…

Obstacle avoidance from monocular images is a challenging problem for robots. Though multi-view structure-from-motion could build 3D maps, it is not robust in textureless environments. Some learning based methods exploit human demonstration…

This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a…

Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to…

This paper presents an self-supervised deep learning network for monocular visual inertial odometry (named DeepVIO). DeepVIO provides absolute trajectory estimation by directly merging 2D optical flow feature (OFF) and Inertial Measurement…

Event cameras provide a natural and data efficient representation of visual information, motivating novel computational strategies towards extracting visual information. Inspired by the biological vision system, we propose a behavior driven…

Human beings have the ability to continuously analyze a video and immediately extract the motion components. We want to adopt this paradigm to provide a coherent and stable motion segmentation over the video sequence. In this perspective,…

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or…

Multisensor fusion is essential for autonomous vehicles to accurately perceive, analyze, and plan their trajectories within complex environments. This typically involves the integration of data from LiDAR sensors and cameras, which…

Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian motion guidance, where optical flow is estimated relative to…

We present a novel method for multi-view depth estimation from a single video, which is a critical task in various applications, such as perception, reconstruction and robot navigation. Although previous learning-based methods have…