Yu-Lun Liu

I am a fourth year PhD student working with Yung-Yu Chuang in the CSIE department at National Taiwan University. I work on problems in computer vision, machine learning, and multimedia.

I am also a senior algorithm development engineer at MediaTek Inc., where I work on computational photography, computer vision, and machine learning.

I did my undergrad and bachelors at National Chiao Tung University.

Email  /  CV  /  Google Scholar  /  Facebook  /  Instagram  /  Github

In this paper, a learning-based multimodal tone-mapping method is proposed, which not only achieves excellent visual quality but also explores the style diversity.

We propose a data-driven approach, where a generative noise model is learned from real-world noise.

In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model.

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera.

For utilizing the views more effectively and reducing redundancy within views, we propose a view selection module that generates an attention map indicating the importance of each view and its potential for contributing to accurate depth estimation.

The cycle consistency loss can better utilize the training data to not only enhance the interpolation results, but also maintain the performance better with less training data.

This paper mainly focuses on creating a global background model of a video sequence using the depth maps together with the RGB pictures.

In this study, we propose a backward warping process to replace the forward warping process, and the artifacts (particularly the ones produced by quantization) are significantly reduced.

Stolen from Jon Barron's website.
Last updated December 2020.