FRONT
发表于 2025-3-30 09:19:37
http://reply.papertrans.cn/25/2424/242323/242323_51.png
召集
发表于 2025-3-30 15:44:57
http://reply.papertrans.cn/25/2424/242323/242323_52.png
LEVY
发表于 2025-3-30 20:25:45
http://reply.papertrans.cn/25/2424/242323/242323_53.png
开花期女
发表于 2025-3-30 21:15:25
http://reply.papertrans.cn/25/2424/242323/242323_54.png
Notify
发表于 2025-3-31 02:34:28
http://reply.papertrans.cn/25/2424/242323/242323_55.png
HERE
发表于 2025-3-31 08:44:37
,ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild,global optimization jointly optimizes the shape, appearance, and deformations of the human body and clothing via multi-layer differentiable volume rendering. To evaluate ReLoo, we record subjects with dynamically deforming garments in a multi-view capture studio. This evaluation, both on existing an
煤渣
发表于 2025-3-31 13:01:41
,Weakly-Supervised Camera Localization by Ground-to-Satellite Image Registration,ve and negative satellite images for each ground image and leverages contrastive learning to learn feature representations for ground and satellite images useful for translation estimation. We also propose a self-supervision strategy for cross-view image relative rotation estimation, which trains th
scrutiny
发表于 2025-3-31 14:42:23
http://reply.papertrans.cn/25/2424/242323/242323_58.png
最高峰
发表于 2025-3-31 20:21:12
,Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraprocess. Furthermore, by incorporating contrastive prompt loss, we ensures distinctive representations for both types of prompts by a mutual pushing strategy. Experimental results demonstrate that our method achieves state-of-the-art performance across various synthetic and real-world datasets, mark
四指套
发表于 2025-4-1 00:50:08
,MoE-DiffIR: Task-Customized Diffusion Priors for Universal Compressed Image Restoration,n to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on unive