Zobrazeno 1 - 10
of 715
pro vyhledávání: '"ZHANG, YANHAO"'
Autor:
Yang, Fan, Zhen, Ru, Wang, Jianing, Zhang, Yanhao, Chen, Haoxiang, Lu, Haonan, Zhao, Sicheng, Ding, Guiguang
AIGC images are prevalent across various fields, yet they frequently suffer from quality issues like artifacts and unnatural textures. Specialized models aim to predict defect region heatmaps but face two primary challenges: (1) lack of explainabilit
Externí odkaz:
http://arxiv.org/abs/2411.17261
We introduce a novel time-varying step-size for the classical projected subgradient method, offering optimal ergodic convergence. Importantly, this approach does not depend on the Lipschitz assumption of the objective function, thereby broadening the
Externí odkaz:
http://arxiv.org/abs/2410.22336
Autor:
Yang, Fan, Zhao, Sicheng, Zhang, Yanhao, Chen, Haoxiang, Chen, Hui, Tang, Wenbo, Lu, Haonan, Xu, Pengfei, Yang, Zhenyu, Han, Jungong, Ding, Guiguang
Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, particularly small models, struggle with processing logical reasonin
Externí odkaz:
http://arxiv.org/abs/2408.07422
3D Gaussian splatting (3DGS) has shown promising results in image rendering and surface reconstruction. However, its potential in volumetric reconstruction tasks, such as X-ray computed tomography, remains under-explored. This paper introduces R$^2$-
Externí odkaz:
http://arxiv.org/abs/2405.20693
Autor:
Zhu, Bingwen, Wang, Fanyi, Lu, Tianyi, Liu, Peng, Su, Jingwen, Liu, Jinxiu, Zhang, Yanhao, Wu, Zuxuan, Qi, Guo-Jun, Jiang, Yu-Gang
Image-to-video (I2V) generation aims to create a video sequence from a single image, which requires high temporal coherence and visual fidelity. However, existing approaches suffer from inconsistency of character appearances and poor preservation of
Externí odkaz:
http://arxiv.org/abs/2404.13680
Autor:
Wang, Fanyi, Liu, Peng, Hu, Haotian, Meng, Dan, Su, Jingwen, Xu, Jinjin, Zhang, Yanhao, Ren, Xiaoming, Zhang, Zhiwang
Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require seamless looping
Externí odkaz:
http://arxiv.org/abs/2404.09172
Autor:
Zhang, Yanhao, Shi, Yujiao, Wang, Shan, Vora, Ankit, Perincherry, Akhil, Chen, Yongbo, Li, Hongdong
Vision-based localization for autonomous driving has been of great interest among researchers. When a pre-built 3D map is not available, the techniques of visual simultaneous localization and mapping (SLAM) are typically adopted. Due to error accumul
Externí odkaz:
http://arxiv.org/abs/2404.09169
Autor:
Wang, Shan, Nguyen, Chuong, Liu, Jiawei, Zhang, Kaihao, Luo, Wenhan, Zhang, Yanhao, Muthu, Sundaram, Maken, Fahira Afzal, Li, Hongdong
Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and (2) highl
Externí odkaz:
http://arxiv.org/abs/2404.07626
This paper introduces a novel prior called Diversified Block Sparse Prior to characterize the widespread block sparsity phenomenon in real-world data. By allowing diversification on intra-block variance and inter-block correlation matrices, we effect
Externí odkaz:
http://arxiv.org/abs/2402.04646
We establish the optimal ergodic convergence rate for the classical projected subgradient method with a time-varying step-size. This convergence rate remains the same even if we slightly increase the weight of the most recent points, thereby relaxing
Externí odkaz:
http://arxiv.org/abs/2402.10221