Optical Diffusion Models for Image Generation

no code implementations • 15 Jul 2024 • Ilker Oguz, Niyazi Ulas Dinc, Mustafa Yıldırım, Junjie Ke, Innfarn Yoo, Qifei Wang, Feng Yang, Christophe Moser, Demetri Psaltis

Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution.

Denoising Image Generation

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

no code implementations • 11 Jan 2024 • Seung Hyun Lee, Yinxiao Li, Junjie Ke, Innfarn Yoo, Han Zhang, Jiahui Yu, Qifei Wang, Fei Deng, Glenn Entis, Junfeng He, Gang Li, Sangpil Kim, Irfan Essa, Feng Yang

We use the novel multi-reward optimization algorithm to jointly optimize the T2I model and a prompt expansion network, resulting in significant improvement of image quality and also allow to control the trade-off of different rewards using a reward related prompt during inference.

Reinforcement Learning (RL) Text-to-Image Generation

Soundini: Sound-Guided Diffusion for Natural Video Editing

1 code implementation • 13 Apr 2023 • Seung Hyun Lee, Sieun Kim, Innfarn Yoo, Feng Yang, Donghyeon Cho, Youngseo Kim, Huiwen Chang, Jinkyu Kim, Sangpil Kim

We propose a method for adding sound-guided visual effects to specific regions of videos with a zero-shot setting.

Denoising Optical Flow Estimation +1

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings

no code implementations • CVPR 2022 • Innfarn Yoo, Huiwen Chang, Xiyang Luo, Ondrej Stava, Ce Liu, Peyman Milanfar, Feng Yang

Digital watermarking is widely used for copyright protection.

Decoder

GIFnets: Differentiable GIF Encoding Framework

no code implementations • CVPR 2020 • Innfarn Yoo, Xiyang Luo, Yilin Wang, Feng Yang, Peyman Milanfar

DitherNet manipulates the input image to reduce color banding artifacts and provides an alternative to traditional dithering.