54 citations · 58 across the 3 of their papers we have counts for
3 papers
cs.LG2025★ 1 cited
In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models
Enhao Gu, Haolin Hou
The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models. The popular classifier-free guidance (CFG) approach impro…
cs.CV2022★ 54 cited
Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution
Hao Hou, Jun Xu, Yingkun Hou +3
Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on f…
eess.IV2021★ 3 cited
NLHD: A Pixel-Level Non-Local Retinex Model for Low-Light Image Enhancement
Hao Hou, Yingkun Hou, Yuxuan Shi +2
Retinex model has been applied to low-light image enhancement in many existing methods. More appropriate decomposition of a low-light image can help achieve better image enhancemen…