2 papers
cs.CV2026
Inference-time Trajectory Optimization for Structure-Preserving Manga Image Editing
Ryosuke Furuta
We present a lightweight, training-free trajectory correction method that adapts a pretrained image editing model to each input manga image using only the input itself. Despite rec…
cs.CV2024
Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga
Takara Taniguchi, Ryosuke Furuta
We tackle one-shot object detection in Japanese Manga. The rising global popularity of Japanese manga has made the object detection of character faces increasingly important, with…