Related papers: RobustFusion: Robust Volumetric Performance Recons…

We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively…

The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways. The main elements of an integrated platform, which target tele-immersion and future 3D applications, are described in…

We introduce a novel robust hybrid 3D face tracking framework from RGBD video streams, which is capable of tracking head pose and facial actions without pre-calibration or intervention from a user. In particular, we emphasize on improving…

Recent advancements in sensor technology and deep learning have led to significant progress in 3D human body reconstruction. However, most existing approaches rely on data from a specific sensor, which can be unreliable due to the inherent…

While the keypoint-based maps created by sparse monocular simultaneous localisation and mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desired for many robotic tasks. Solutions involving depth cameras…

Depth estimation provides an alternative approach for perceiving 3D information in autonomous driving. Monocular depth estimation, whether with single-frame or multi-frame inputs, has achieved significant success by learning various types…

This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. Previous approaches treat dynamic…

We propose VisFusion, a visibility-aware online 3D scene reconstruction approach from posed monocular videos. In particular, we aim to reconstruct the scene from volumetric features. Unlike previous reconstruction methods which aggregate…

Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

Recent years have witnessed tremendous progress in the 3D reconstruction of dynamic humans from a monocular video with the advent of neural rendering techniques. This task has a wide range of applications, including the creation of virtual…

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition…

Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Radar-based perception suffers from its unintuitive sensing…

Recovering textured 3D models of non-rigid human body shapes is challenging due to self-occlusions caused by complex body poses and shapes, clothing obstructions, lack of surface texture, background clutter, sparse set of cameras with…

Collaborative visual perception methods have gained widespread attention in the autonomous driving community in recent years due to their ability to address sensor limitation problems. However, the absence of explicit depth information…

Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…

Collaborative perception is dedicated to tackling the constraints of single-agent perception, such as occlusions, based on the multiple agents' multi-view sensor inputs. However, most existing works assume an ideal condition that all…

Multi-modal 3D object detectors are dedicated to exploring secure and reliable perception systems for autonomous driving (AD).Although achieving state-of-the-art (SOTA) performance on clean benchmark datasets, they tend to overlook the…

Capturing general deforming scenes from monocular RGB video is crucial for many computer graphics and vision applications. However, current approaches suffer from drawbacks such as struggling with large scene deformations, inaccurate shape…

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image.…