Zobrazeno 61 - 70
of 320
pro vyhledávání: '"Liu, Yong"'
Autor:
He, Yuze, Bai, Yushi, Lin, Matthieu, Zhao, Wang, Hu, Yubin, Sheng, Jenny, Yi, Ran, Li, Juanzi, Liu, Yong-Jin
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3D data. Due to the open-ended nature of the task, most studies evaluat
Externí odkaz:
http://arxiv.org/abs/2310.02977
Autor:
Sun, Zhiyao, Lv, Tian, Ye, Sheng, Lin, Matthieu, Sheng, Jenny, Wen, Yu-Hui, Yu, Minjing, Liu, Yong-Jin
The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the corresponding natural facial motion. However, existing methods either emp
Externí odkaz:
http://arxiv.org/abs/2310.00434
This paper presents a flexible representation of neural radiance fields based on multi-plane images (MPI), for high-quality view synthesis of complex scenes. MPI with Normalized Device Coordinate (NDC) parameterization is widely used in NeRF learning
Externí odkaz:
http://arxiv.org/abs/2310.00249
Query-based object detectors have made significant advancements since the publication of DETR. However, most existing methods still rely on multi-stage encoders and decoders, or a combination of both. Despite achieving high accuracy, the multi-stage
Externí odkaz:
http://arxiv.org/abs/2309.16306
Autor:
Liu, Jiaqi, Xie, Guoyang, Chen, Ruitao, Li, Xinpeng, Wang, Jinbao, Liu, Yong, Wang, Chengjie, Zheng, Feng
High-precision point cloud anomaly detection is the gold standard for identifying the defects of advancing machining and precision manufacturing. Despite some methodological advances in this area, the scarcity of datasets and the lack of a systematic
Externí odkaz:
http://arxiv.org/abs/2309.13226
Cross-modality point cloud registration is confronted with significant challenges due to inherent differences in modalities between different sensors. We propose a cross-modality point cloud registration framework FF-LOGO: a cross-modality point clou
Externí odkaz:
http://arxiv.org/abs/2309.08966
The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by predicted surfa
Externí odkaz:
http://arxiv.org/abs/2309.07640
Autor:
Jiang, Chenyao, Zhai, Shiyao, Song, Hengrui, Ma, Yuqing, Fan, Yachen, Fang, Yancheng, Yu, Dongmei, Zhang, Canyang, Han, Sanyang, Wang, Runming, Liu, Yong, Li, Jianbo, Qin, Peiwu
Dental caries is one of the most common oral diseases that, if left untreated, can lead to a variety of oral problems. It mainly occurs inside the pits and fissures on the occlusal/buccal/palatal surfaces of molars and children are a high-risk group
Externí odkaz:
http://arxiv.org/abs/2308.16551
Autor:
Fu, Weifu, Nie, Qiang, Li, Jialin, Lin, Yuhuan, Wu, Kai, Li, Jian, Wang, Yabiao, Liu, Yong, Wang, Chengjie
Despite recent advances in semantic segmentation, an inevitable challenge is the performance degradation caused by the domain shift in real applications. Current dominant approach to solve this problem is unsupervised domain adaptation (UDA). However
Externí odkaz:
http://arxiv.org/abs/2308.15855
Visual bird's eye view (BEV) semantic segmentation helps autonomous vehicles understand the surrounding environment only from images, including static elements (e.g., roads) and dynamic elements (e.g., vehicles, pedestrians). However, the high cost o
Externí odkaz:
http://arxiv.org/abs/2308.14525