抛物线 发表于 2025-3-25 03:21:34

,Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats,e real-world experiments, we demonstrate our method, Flash-Splat, accurately reconstructs both transmitted and reflected scenes in 3D. Our method outperforms existing 3D reflection separation methods, which do not leverage illumination control, by a large margin.

Accede 发表于 2025-3-25 08:09:39

http://reply.papertrans.cn/25/2424/242353/242353_22.png

慷慨援助 发表于 2025-3-25 13:47:59

0302-9743 reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; motion estimation..978-3-031-73006-1978-3-031-73007-8Series ISSN 0302-9743 Series E-ISSN 1611-3349

暴发户 发表于 2025-3-25 18:34:10

http://reply.papertrans.cn/25/2424/242353/242353_24.png

grenade 发表于 2025-3-25 22:15:07

http://reply.papertrans.cn/25/2424/242353/242353_25.png

轻快带来危险 发表于 2025-3-26 01:51:34

https://doi.org/10.1007/978-3-319-01119-6in improved image quality. Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8.14 and surpassing all GAN-based and multi-step Stable Diffusion models.

仲裁者 发表于 2025-3-26 06:06:12

Karen Insa Wolf,Stefan Goetze,Frank Wallhoffmodel benchmarks demonstrate that DiffSurf can generate shapes with greater diversity and higher quality than previous generative models. Furthermore, when applied to the task of single-image 3D human mesh recovery, DiffSurf achieves accuracy comparable to prior techniques at a near real-time rate.

BLOT 发表于 2025-3-26 10:44:06

SwiftBrush V2: Make Your One-Step Diffusion Model Better Than Its Teacher,in improved image quality. Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8.14 and surpassing all GAN-based and multi-step Stable Diffusion models.

Ballad 发表于 2025-3-26 15:07:31

http://reply.papertrans.cn/25/2424/242353/242353_29.png

neolith 发表于 2025-3-26 19:31:33

http://reply.papertrans.cn/25/2424/242353/242353_30.png
页: 1 2 [3] 4 5 6 7
查看完整版本: Titlebook: Computer Vision – ECCV 2024; 18th European Confer Aleš Leonardis,Elisa Ricci,Gül Varol Conference proceedings 2025 The Editor(s) (if applic