骑师 发表于 2025-3-25 07:18:40

http://reply.papertrans.cn/24/2342/234134/234134_21.png

Anthropoid 发表于 2025-3-25 08:50:03

Multi-granularity Transformer for Image Super-Resolutionntly aggregate both local and global information for accurate reconstruction. Extensive experiments on five benchmark datasets demonstrate that our MugFormer performs favorably against state-of-the-art methods in terms of both quantitative and qualitative results.

呼吸 发表于 2025-3-25 15:11:18

http://reply.papertrans.cn/24/2342/234134/234134_23.png

高度表 发表于 2025-3-25 19:15:50

DualBLN: Dual Branch LUT-Aware Network for Real-Time Image Retouchingwe employ bilinear pooling to solve the problem of feature information loss that occurs when fusing features from the dual branch network, avoiding the feature distortion caused by direct concatenation or summation. Extensive experiments on several datasets demonstrate the effectiveness of our work,

贵族 发表于 2025-3-25 20:46:12

CSIE: Coded Strip-Patterns Image Enhancement Embedded in Structured Light-Based MethodsIE results can be achieved accordingly and further improve the details performance of 3D model reconstruction. Experiments on multiple sets of challenging CSI sequences show that our CSIE outperforms the existing used for natural image-enhanced methods in terms of 2D enhancement, point clouds extrac

溃烂 发表于 2025-3-26 03:11:28

http://reply.papertrans.cn/24/2342/234134/234134_26.png

Indolent 发表于 2025-3-26 04:58:13

http://reply.papertrans.cn/24/2342/234134/234134_27.png

PIZZA 发表于 2025-3-26 11:07:33

http://reply.papertrans.cn/24/2342/234134/234134_28.png

玛瑙 发表于 2025-3-26 15:30:39

MatchFormer: Interleaving Attention in Transformers for Feature MatchingMatchFormer is a multi-win solution in efficiency, robustness, and precision. Compared to the previous best method in indoor pose estimation, our lite MatchFormer has only . GFLOPs, yet achieves a . precision gain and a . running speed boost. The large MatchFormer reaches state-of-the-art on four di

gentle 发表于 2025-3-26 20:06:11

http://reply.papertrans.cn/24/2342/234134/234134_30.png
页: 1 2 [3] 4 5 6
查看完整版本: Titlebook: Computer Vision – ACCV 2022; 16th Asian Conferenc Lei Wang,Juergen Gall,Rama Chellappa Conference proceedings 2023 The Editor(s) (if applic