CVPR

Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention

Kyungmin Jo, Jooyeol Yun, Jaegul Choo

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） 纠错

Journal ref CVPR 2025

IAUNet: Instance-Aware U-Net

Yaroslav Prytula, Illia Tsiporenko, Ali Zeynalli, Dmytro Fishman

机构 * Institute of Computer Science, University of Tartu（塔尔图大学计算机科学研究所） ； Ukrainian Catholic University（乌克兰天主教大学） ； STACC OÜ（STACC公司） 纠错

Comments Published in CVPR Workshops (CVMI), 2025. Project page/code/models/dataset: $\href{https://slavkoprytula.github.io/IAUNet/}{\text{this https URL}}$

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025, pp. 4739-4748

Scaling Vision Pre-Training to 4K Resolution

Baifeng Shi, Boyi Li, Han Cai, Yao Lu, Sifei Liu, Marco Pavone, Jan Kautz, Song Han, Trevor Darrell, Pavlo Molchanov, Hongxu Yin

机构 * UC Berkeley（加州大学伯克利分校） ； NVIDIA（英伟达） 纠错

Comments CVPR 2025. Project Page: https://nvlabs.github.io/PS3

Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation

Nadav Z. Cohen, Oron Nir, Ariel Shamir

机构 * Reichman University（里奇曼大学） ； Microsoft Corporation（微软公司） 纠错

Comments Conference paper at CVPR 2025. Project page: https://nadavc220.github.io/conditional-balance.github.io/