Zobrazeno 1 - 10
of 962
pro vyhledávání: '"Xu, Hongbin"'
3D neural style transfer has gained significant attention for its potential to provide user-friendly stylization with spatial consistency. However, existing 3D style transfer methods often fall short in terms of inference efficiency, generalization a
Externí odkaz:
http://arxiv.org/abs/2410.10412
Autor:
Xu, Hongbin, Chen, Weitao, Zhou, Zhipeng, Xiao, Feng, Sun, Baigui, Shou, Mike Zheng, Kang, Wenxiong
Despite recent advancements in 3D generation methods, achieving controllability still remains a challenging issue. Current approaches utilizing score-distillation sampling are hindered by laborious procedures that consume a significant amount of time
Externí odkaz:
http://arxiv.org/abs/2410.09592
3D biometric techniques on finger traits have become a new trend and have demonstrated a powerful ability for recognition and anti-counterfeiting. Existing methods follow an explicit 3D pipeline that reconstructs the models first and then extracts fe
Externí odkaz:
http://arxiv.org/abs/2410.09582
We introduce GaussianOcc, a systematic method that investigates the two usages of Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views. First, traditional methods for self-supervised 3D occupancy estima
Externí odkaz:
http://arxiv.org/abs/2408.11447
Remote Photoplethysmography (rPPG) is a non-contact technique for extracting physiological signals from facial videos, used in applications like emotion monitoring, medical assistance, and anti-face spoofing. Unlike controlled laboratory settings, re
Externí odkaz:
http://arxiv.org/abs/2408.01077
Despite the impressive performance of Multi-view Stereo (MVS) approaches given plenty of training samples, the performance degradation when generalizing to unseen domains has not been clearly explored yet. In this work, we focus on the domain general
Externí odkaz:
http://arxiv.org/abs/2405.09131
4D style transfer aims at transferring arbitrary visual style to the synthesized novel views of a dynamic 4D scene with varying viewpoints and times. Existing efforts on 3D style transfer can effectively combine the visual features of style images an
Externí odkaz:
http://arxiv.org/abs/2403.08310
3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in the descr
Externí odkaz:
http://arxiv.org/abs/2403.08182
Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably, self-attentio
Externí odkaz:
http://arxiv.org/abs/2310.06470
Autor:
Chen, Weitao, Xu, Hongbin, Zhou, Zhipeng, Liu, Yang, Sun, Baigui, Kang, Wenxiong, Xie, Xuansong
The core of Multi-view Stereo(MVS) is the matching process among reference and source pixels. Cost aggregation plays a significant role in this process, while previous methods focus on handling it via CNNs. This may inherit the natural limitation of
Externí odkaz:
http://arxiv.org/abs/2305.10320