Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

1 code implementation • 22 Nov 2023 • Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, Kiyoharu Aizawa

We show that a simple retrieval augmentation can significantly improve the generation quality.

Retrieval

Memory Efficient Diffusion Probabilistic Models via Patch-based Generation

no code implementations • 14 Apr 2023 • Shinei Arakawa, Hideki Tsunashima, Daichi Horita, Keitaro Tanaka, Shigeo Morishima

Second, we propose Global Content Conditioning (GCC) to ensure patches have coherent content when concatenated together.

A Structure-Guided Diffusion Model for Large-Hole Image Completion

1 code implementation • 18 Nov 2022 • Daichi Horita, Jiaolong Yang, Dong Chen, Yuki Koyama, Kiyoharu Aizawa, Nicu Sebe

The structure generator generates an edge image representing plausible structures within the holes, which is then used for guiding the texture generation process.

Denoising Texture Synthesis

SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal

no code implementations • 16 Sep 2020 • Daichi Horita, Kiyoharu Aizawa

Furthermore, we show that our proposal can interpolate facial makeup images to determine the unique features, compare existing methods, and help users find desirable makeup configurations.

Generative Adversarial Network