Related papers: RobustFusion: Robust Volumetric Performance Recons…
This paper introduces a novel deep learning-based multimodal fusion architecture aimed at enhancing the perception capabilities of autonomous navigation robots in complex environments. By utilizing innovative feature extraction modules,…
Recently, the RGB images and point clouds fusion methods have been proposed to jointly estimate 2D optical flow and 3D scene flow. However, as both conventional RGB cameras and LiDAR sensors adopt a frame-based data acquisition mechanism,…
Robust Subspace Recovery (RoSuRe) algorithm was recently introduced as a principled and numerically efficient algorithm that unfolds underlying Unions of Subspaces (UoS) structure, present in the data. The union of Subspaces (UoS) is…
Object reconstruction from 3D point clouds has been a long-standing research problem in computer vision and computer graphics, and achieved impressive progress. However, reconstruction from time-varying point clouds (a.k.a. 4D point clouds)…
Despite the recent developments in 3D Face Reconstruction from occluded and noisy face images, the performance is still unsatisfactory. Moreover, most existing methods rely on additional dependencies, posing numerous constraints over the…
A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of…
3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or time-consuming per-subject optimization procedures. To…
Human-centric volumetric videos offer immersive free-viewpoint experiences, yet existing methods focus either on replaying general dynamic scenes or animating human avatars, limiting their ability to re-perform general dynamic scenes. In…
Comprehensive perception of human beings is the prerequisite to ensure the safety of human-robot interaction. Currently, prevailing visual sensing approach typically involves a single static camera, resulting in a restricted and occluded…
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…
Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation,…
This paper proposes a real-time dynamic scene reconstruction method capable of reproducing the motion, geometry, and segmentation simultaneously given live depth stream from a single RGB-D camera. Our approach fuses geometry frame by frame…
Sharing live telepresence experiences for teleconferencing or remote collaboration receives increasing interest with the recent progress in capturing and AR/VR technology. Whereas impressive telepresence systems have been proposed on top of…
Monocular 3D clothed human reconstruction aims to create a complete 3D avatar from a single image. To tackle the human geometry lacking in one RGB image, current methods typically resort to a preceding model for an explicit geometric…
Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
We introduce UniCon3R, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffer from artifacts, where bodies float above the ground or…
Transparent object perception is indispensable for numerous robotic tasks. However, accurately segmenting and estimating the depth of transparent objects remain challenging due to complex optical properties. Existing methods primarily delve…
Reconstructing 3D human bodies from realistic motion sequences remains a challenge due to pervasive and complex occlusions. Current methods struggle to capture the dynamics of occluded body parts, leading to model penetration and distorted…
Human activities are inherently complex, often involving numerous object interactions. To better understand these activities, it is crucial to model their interactions with the environment captured through dynamic changes. The recent…