Yu-Ting Wu (吳昱霆)

Technical Manager
MediaTek Inc.

kevincosnerwu [at] gmail.com

Curriculum Vitae [Sep. 2021]

Recent News

Time Event
Sep. 2021 I have joined MediaTek Inc. as a technical manager
Aug. 2021 Our paper, "Learning to Cluster for Rendering with Many Lights", is accepted to SIGGRAPH Asia 2021
May 2021 Our paper, "Multi-Resolution Shared Representative Filtering for Real-Time Depth Completion", is accepted to High-Performance Graphics 2021
Dec. 2020 Our paper, "ClipFlip: Multi-view Clipart Design", is accepted to Computer Graphics Forum
Sep. 2020 My son was born!
Feb. 2020 I have Joined Communication and Multimedia Laboratory (CMLab) of National Taiwan University as a postdoctoral researcher


I am currently a technical manager at MediaTek. Before joining MediaTek, I was a postdoctoral researcher at Communication and Multimedia Laboratory (CMLab), National Taiwan University. I recieved my bachelor's degree and master's degree in National Chiao Tung University (NCTU) in 2007 and 2009, respectively. After that, I continued my research with Prof. Yung-Yu Chuang in National Taiwan University (NTU) and defended my Ph.D. degree in 2014. During the period 2014 to 2019, I worked as a software engineer at HTC and Toppano, mainly in charge of developing computer graphics and computational photography techniques for VR and MR applications. My research interests include computer graphics, computational photography, GPU architectures and programming, AR/MR/VR, image processing, and machine learning.


Technical Manager - MediaTek, Sep. 2021 - Now

Postdoctoral Researcher - National Taiwan University, Feb. 2020 - Jul. 2021

Senior Algorithm Developer - Toppano Inc. (a startup company), May 2018 - Jan. 2020

Principal Engineer - HTC Inc., Sep. 2014 - Apr. 2018

Summer Intern - Digimax Inc., Jul. 2011 - Sep. 2011

Teaching Assistant (Digital Image Synthesis) - National Taiwan University, Fall 2009 - 2013 (five times)

Teaching Assistant (Computer Graphics) - National Chiao Tung University, Fall 2008

Selected Publications

Categorized by:   Computer Graphics CG   Computer Vision CV   Image Processing IP   Artificial Intelligence AI  

Learning to Cluster for Rendering with Many Lights   CG AI
Yu-Chen Wang, Yu-Ting Wu*, Tzu-Mao Li, Yung-Yu Chuang (*: the corresponding author)
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2021), to appear
(a progressive many-light rendering algorithm that can learn to cluster and sample lights)

     We present an unbiased online Monte Carlo method for rendering with many lights. Our method adapts both the hierarchical light clustering and the sampling distribution to our collected samples. Designing such a method requires us to make clustering decisions under noisy observation, and making sure that the sampling distribution adapts to our target. Our method is based on two key ideas: a coarse-to-fine clustering scheme that can find good clustering configurations even with noisy samples, and a discrete stochastic successive approximation method that starts from a prior distribution and provably converges to a target distribution. We compare to other state-of-the-art light sampling methods, and show better results both numerically and visually.

Project Page Paper Citation

Multi-Resolution Shared Representative Filtering for Real-Time Depth Completion   CG CV IP
Yu-Ting Wu, Tzu-Mao Li, I-Chao Shen, Hong-Shiang Lin, Yung-Yu Chuang
High-Performance Graphics 2021
(a real-time depth completion algorithm for effectively handling large missing regions of depth maps)

     We present shared representative filtering for real-time high-resolution depth completion with RGB-D sensors. Conventional filtering-based methods face a dilemma when the missing regions of the depth map are large. When the filter window is small, the filter fails to include enough samples. On the other hand, when the window is large, the method could oversmooth depth boundaries due to the error introduced by the extra samples. Our method adapts the filter kernels to the shape of the missing regions to collect a sufficient number of samples while avoiding oversmoothing. We collect depth samples by searching for a small set of similar pixels, which we call the representatives, using an efficient line search algorithm. We then combine the representatives using a joint bilateral weight. Experiments show that our method can filter a high-resolution depth map within a few milliseconds while outperforming previous filtering-based methods on both real-world and synthetic data in terms of both efficiency and accuracy, especially when dealing with large missing regions in depth maps.

Project Page Paper Slides Citation Digital Library

ClipFlip: Multi-view Clipart Design   CG CV AI
I-Chao Shen, Kuan-Hung Liu, Li-Wen Su, Yu-Ting Wu, Bing-Yu Chen
Computer Graphics Forum, February 2021
(an assistive system for clipart design by providing visual scaffolds from the unseen view points)

     We present an assistive system for clipart design by providing visual scaffolds from the unseen viewpoints. Inspired by the artists’ creation process, our system constructs the visual scaffold by first synthesizing the reference 3D shape of the input clipart and rendering it from the desired viewpoint. The critical challenge of constructing this visual scaffold is to generate a reference 3D shape that matches the user’s expectations in terms of object sizing and positioning while preserving the geometric style of the input clipart. To address this challenge, we propose a user-assisted curve extrusion method to obtain the reference 3D shape. We render the synthesized reference 3D shape with a consistent style into the visual scaffold. By following the generated visual scaffold, the users can efficiently design clipart with their desired viewpoints. The user study conducted by an intuitive user interface and our generated visual scaffold suggests that our system is especially useful for estimating the ratio and scale between object parts and can save on average 57% of drawing time.

Project Page Paper Citation arXiv version Digital Library

Dual-Matrix Sampling for Scalable Translucent Material Rendering   CG
Yu-Ting Wu, Tzu-Mao Li, Yu-Hsun Lin, Yung-Yu Chuang
IEEE Transactions on Visualization and Computer Graphics, March 2015
(a scalable algorithm for rendering plenty of translucent objects under complex illumination)

     This paper introduces a scalable algorithm for rendering translucent materials with complex lighting. We represent the light transport with a diffusion approximation by a dual-matrix representation with the Light-to-Surface and Surface-to-Camera matrices. By exploiting the structures within the matrices, the proposed method can locate surface samples with little contribution by using only subsampled matrices and avoid wasting computation on these samples. The decoupled estimation of irradiance and diffuse BSSRDFs also allows us to have a tight error bound, making the adaptive diffusion approximation more efficient and accurate. Experiments show that our method outperforms previous methods for translucent material rendering, especially in large scenes with massive translucent surfaces shaded by complex illumination.

Project Page Paper Citation Digital Library

VisibilityCluster: Average Directional Visibility for Many-Light Rendering   CG
Yu-Ting Wu, Yung-Yu Chuang
IEEE Transactions on Visualization and Computer Graphics, September 2013
(a method for efficient computation and compact representation of the visibility function for many-light rendering)

     This paper proposes the VisibilityCluster algorithm for efficient visibility approximation and representation in many-light rendering. By carefully clustering lights and shading points, we can construct a visibility matrix that exhibits good local structures due to visibility coherence of nearby lights and shading points. Average visibility can be efficiently estimated by exploiting the sparse structure of the matrix and shooting only few shadow rays between clusters. Moreover, we can use the estimated average visibility as a quality measure for visibility estimation, enabling us to locally refine VisibilityClusters with large visibility variance for improving accuracy. We demonstrate that, with the proposed method, visibility can be incorporated into importance sampling at a reasonable cost for the manylight problem, significantly reducing variance in Monte Carlo rendering. In addition, the proposed method can be used to increase realism of local shading by adding directional occlusion effects. Experiments show that the proposed technique outperforms state-ofthe-art importance sampling algorithms, and successfully enhances the preview quality for lighting design.

Project Page Paper Citation Digital Library

SURE-based Optimization for Adaptive Sampling and Reconstruction   CG
Tzu-Mao Li, Yu-Ting Wu, Yung-Yu Chuang
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2012),
(an adaptive sampling and denoising method for Monte Carlo rendering using Stein's unbiased risk estimator)

     We apply Stein’s Unbiased Risk Estimator (SURE) to adaptive sampling and reconstruction to reduce noise in Monte Carlo rendering. SURE is a general unbiased estimator for mean squared error (MSE) in statistics. With SURE, we are able to estimate error for an arbitrary reconstruction kernel, enabling us to use more effective kernels rather than being restricted to the symmetric ones used in previous work. It also allows us to allocate more samples to areas with higher estimated MSE. Adaptive sampling and reconstruction can therefore be processed within an optimization framework. We also propose an efficient and memory-friendly approach to reduce the impact of noisy geometry features where there is depth of field or motion blur. Experiments show that our method produces images with less noise and crisper details than previous methods.

Project Page Paper Slides Citation Digital Library

VisibilityChuck: Average Directional Visibility for Importance Sampling   CG
Yu-Ting Wu, Yung-Yu Chuang
ACM SIGGRAPH Asia 2012 Poster,
(an early version of our VisibilityCluster paper)

Paper Digital Library

Ph.D. Dissertation

Sampling and Reconstruction Techniques for Efficient Monte Carlo Rendering   CG
Yu-Ting Wu, advised by Yung-Yu Chuang
Doctor of Philosophy in Computer Science and Information Engineering, National Taiwan University, June 2014
(a coherent view of my Ph.D. research with background reviews)

     Two of the most important tasks that computer graphics techniques try to solve is rendering photo-realistic images and performing numerically accurate simulation. Physically-based rendering can naturally satisfy these two goals. It is usually simulated by the Monte Carlo ray tracing for handling a variety of sophisticated light transport paths in a united manner. Despite its generality and simplicity, however, Monte Carlo integration converges slowly. Rendering scenes with lots of complex geometry and realistic materials under complex illumination usually requires a large number of samples to produce a noise-free image.
     In this dissertation, we proposed three advanced sampling and reconstruction algorithms for improving the performance of Monte Carlo integration. First, realizing that in complex scenes visibility is usually the major source of noise during sampling the shading function, we developed a method called VisibilityCluster for efficiently approximating visibility function. By integrating it into importance sampling framework, we achieve superior noise reduction compared to previous approaches. Second, to reduce the computation overhead of rendering translucent materials, we proposed an algorithm, Dualmatrix sampling, to avoid evaluating unimportant surface samples which contribute little to the final image. Finally, a general adaptive sampling and reconstruction framework named SURE-based optimization is proposed to render a wide range of distributed effects, including depth of field, motion blur, and global illumination. All of the three methods achieve significant performance improvement compared to the state-of-the-art rendering algorithms.

Dissertation Slides


Electronic device, method for displaying an augmented reality scene and non-transitory computer-readable medium   CG CV
Yu-Ting Wu, Ching-Yang Chen
ROC Patent No: I711966. December 01, 2020
US Patent No: 10636200, April 28, 2020

Virtual reality device, image processing method, and non-transitory computer-readable medium   CG
Yu-Ting Wu, Chun-Wen Cheng, Ching-Yang Chen
ROC Patent No: I684163, February 01, 2020

Three-dimensional modeling method and electronic apparatus thereof   CG CV
Sheng-Jie Luo, Liang-Kang Huang, Yu-Ting Wu, Tung-Peng Wu
US Patent No: 10152827, December 11, 2018


Highlight Paper, SIGGRAPH Asia 2012, Nov. 2012
Highlight Poster, SIGGRAPH Asia 2012, Nov. 2012
Honorary Member, Phi-Tau-Phi Scholastic Honor Society, 2007
Master Freshman Scholarship, National Chiao Tung University, 2007
3rd place at Communication Competition Contest, Ministry of Education, 2006
2nd place at Computer Science Project Competition, National Chiao Tung University, 2006
Academic Excellence Award, National Chiao Tung University, Fall 2006
Academic Excellence Award, National Chiao Tung University, Spring 2006
Academic Excellence Award, National Chiao Tung University, Fall 2005
Academic Excellence Award, National Chiao Tung University, Spring 2005
Academic Excellence Award, National Chiao Tung University, Fall 2004
Academic Excellence Award, National Chiao Tung University, Spring 2004
Academic Excellence Award, National Chiao Tung University, Fall 2003

Professional Services

Reviewer: ICCV 2021, APMAR 2021, CVPR 2020, ECCV 2020, WSCG 2013, The Visual Computer, Journal of Information Science and Engineering
Invited Talk: National Cheng Kung University, May 2016
Invited Talk: Yuan Ze University, May 2016
Invited Talk: Industrial Technology Research Institute (ITRI), Dec. 2013

The design of this webpage is borrowed from Dr. Lingqi Yan

Last Update: September 2021