Yuchen Hong / 洪雨辰

Yuchen Hong is a Ph.D. candidate in the Camera Intelligence Lab of Peking University, supervised by Prof. Boxin Shi. He received the B.E. degree from Beijing University of Posts and Telecommuications (BUPT) in 2020.

Email  /  Google Scholar  /  Linked In

My research interests include physics-/language-/diffusion-based image/video restoration.

This paper investigates the problem of removing strong reflections from contaminated image sequences or videos by exploiting periodically varying light flickering.

This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content information.

This paper proposes the first end-to-end panoramic image reflection removal framework, aiming at reliving the content ambiguity between reflection and transmission scenes.

This paper proposes the SIR2⁺ benchmark dataset with a large number and a great diversity of mixture images, and ground truth of background and reflection.

This paper studies the problem of recovering high frame rate (HFR) and high dynamic range (HDR) color videos from a hybrid camera system composed of a spiking and an alternating-exposure RGB camera.

This paper proposes the NIR and RGB feature fused Reflection Removal Network (NIR³Net) to utilize auxiliary information in active NIR images.

This paper studies the problem of panoramic image reflection removal, aiming at reliving the content ambiguity between reflection and transmission scenes.

This paper proposes a Near-infrared Image guided Reflection Removal Network (NIR²Net) to remove undesired reflections in an RGB image with the guidance of an NIR image.

Thank Dr. Jon Barron for sharing the source code of his personal page.