Region-aware Attention for Image Inpainting
Zhilin Huang, Chujun Qin, Zhenyu Weng, Yuesheng Zhu
Abstract
Recent attention-based image inpainting methods have made inspiring progress by modeling long-range dependencies within a single image. However, they tend to generate blurry contents since the correlation between each pixel pairs is always misled by ill-predicted features in holes. To handle this problem, we propose a novel region-aware attention (RA) module. By avoiding the directly calculating corralation between each pixel pair in a single samples and considering the correlation between different samples, the misleading of invalid information in holes can be avoided. Meanwhile, a learnable region dictionary (LRD) is introduced to store important information in the entire dataset, which not only simplifies correlation modeling, but also avoids information redundancy. By applying RA in our architecture, our methodscan generate semantically plausible results with realistic details. Extensive experiments on CelebA, Places2 and Paris StreetView datasets validate the superiority of our method compared with existing methods.
Create a lesson
Related papers
CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images
Liu Zhenyuan, Bharath Seshadri, Bailey Miller et al.
Visual Marking as a Native Reasoning Capability for Multimodal LLMs
Jiazhen Liu, Yanghao Wang, Chaolei Tan et al.
Self-supervised learning for zebrafish embryo phenotype evaluation: Systematic comparison of algorithms, label-efficient classification, and transfer learning
Thomas Lautenschlager, Gaëlle Hayot, Quentin Brassart et al.
EvoMem3D: Adaptive-Depth Temporal Representation Memory for Multi-Camera 3D Detection
Moshe Kimhi, Idan Kligvasser, Yotam Intrator et al.
Ocular Recognition: Interoperability, Multi-Resolution, and Spectrum Challenges
Fabian Stockhardt, Juan E. Tapia, Christoph Busch
AstroPIE-53: Towards Understanding Failure Modes of Human Pose Estimation in Space
Stephanie Käs, Marten Flaig, Lukas Woyke et al.