Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Zhang, Zhenyu"'
Reconstructing category-specific objects from a single image is a challenging task that requires inferring the geometry and appearance of an object from a limited viewpoint. Existing methods typically rely on local feature retrieval based on re-proje
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61f6da3947ef9e52b3e1da23bf448917
http://arxiv.org/abs/2306.05145
http://arxiv.org/abs/2306.05145
Autor:
Sun, Xiaopeng, Li, Weiqi, Zhang, Zhenyu, Ma, Qiufang, Sheng, Xuhan, Cheng, Ming, Ma, Haoyu, Zhao, Shijie, Zhang, Jian, Li, Junlin, Zhang, Li
360{\deg} omnidirectional images have gained research attention due to their immersive and interactive experience, particularly in AR/VR applications. However, they suffer from lower angular resolution due to being captured by fisheye lenses with the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7e06b889322975bb68d4d893e7cf98d
http://arxiv.org/abs/2304.13471
http://arxiv.org/abs/2304.13471
Autor:
Luo, Simian, Qian, Xuelin, Fu, Yanwei, Zhang, Yinda, Tai, Ying, Zhang, Zhenyu, Wang, Chengjie, Xue, Xiangyang
Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two limitations:
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d07eb8a9ac99505bee8c5ee8ce23dad
http://arxiv.org/abs/2303.14700
http://arxiv.org/abs/2303.14700
Autor:
Tang, Hao, Zhang, Zhenyu, Shi, Humphrey, Li, Bo, Shao, Ling, Sebe, Nicu, Timofte, Radu, Van Gool, Luc
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task. The proposed graph-Transformer-based generator i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1fd3693c7ea19259d69785ceb1318a6
http://arxiv.org/abs/2303.08225
http://arxiv.org/abs/2303.08225
Autor:
Zhang, Zhenyu Charlus, Chaaban, Anas
The dirty paper channel (DPC) under a peak amplitude constraint arises in an optical wireless broadcast channel (BC), where the state at one receiver is the transmitted signal intended for the other receiver(s). This paper studies a class of peak-con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::743e316319bd7a4e9625ebb2c3a0edc0
http://arxiv.org/abs/2301.02306
http://arxiv.org/abs/2301.02306
Autor:
Huang, Tianjin, Yin, Lu, Zhang, Zhenyu, Shen, Li, Fang, Meng, Pechenizkiy, Mykola, Wang, Zhangyang, Liu, Shiwei
This paper reveals a new appeal of the recently emerged large-kernel Convolutional Neural Networks (ConvNets): as the teacher in Knowledge Distillation (KD) for small-kernel ConvNets. While Transformers have led state-of-the-art (SOTA) performance in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5be74b666b7802f56fdbd714a1dca48b
Autor:
Zhang, Zhenyu, Chai, Wenhao, Jiang, Zhongyu, Ye, Tian, Song, Mingli, Hwang, Jenq-Neng, Wang, Gaoang
Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose representations in the shared feature space. In this paper, we propose MPM, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52d65fb00d332a7316b6a3f6ea88927b
Autor:
Yan, Zhiqiang, Zheng, Yupeng, Wang, Kun, Li, Xiang, Zhang, Zhenyu, Chen, Shuo, Li, Jun, Yang, Jian
Depth completion is the task of recovering dense depth maps from sparse ones, usually with the help of color images. Existing image-guided methods perform well on daytime depth perception self-driving benchmarks, but struggle in nighttime scenarios w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e1365673794311dbc344c714a75ae64
Given a robust model trained to be resilient to one or multiple types of distribution shifts (e.g., natural image corruptions), how is that "robustness" encoded in the model weights, and how easily can it be disentangled and/or "zero-shot" transferre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6bbd1dfdf269cd6fb3638462e930193
Autor:
Cheng, Ming, Ma, Haoyu, Ma, Qiufang, Sun, Xiaopeng, Li, Weiqi, Zhang, Zhenyu, Sheng, Xuhan, Zhao, Shijie, Li, Junlin, Zhang, Li
Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based methods in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::902498faf2d2fb555e1bc2dd0a146abe