Cheng Sun

About me

I am a Ph.D. candidate in Institute of Information Systems and Applications at National Tsing Hua University. I have the privilege of working with Prof. Hwann-Tzong Chen at VLLab and Prof. Min Sun at VSLab. I have explored a diverse range of computer vision and deep learning, including 360 panorama, object detection, semantic segmentation, monocular depth estimation, planes detection, layout reconstruction. Currently, I'm focusing on multiviews 3D reconstruction and its applications.

Find my resume here (last update 05/21/2023).



Neural-PBIR Reconstruction of Shape, Material, and Illumination

Cheng Sun*, Guangyan Cai*, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong

under review

Object shape, Physically-based material, Lighting

[Paper] [Project Page]

Multiview Regenerative Morphing with Dual Flows

Chih-Jung Tsai, Cheng Sun, Hwann-Tzong Chen

ECCV 2022

3D morphing, Grid-based NeRF

[Paper] [Codes] [Project Page]

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

Ping-Chung Yu, Cheng Sun, Min Sun

ECCV 2022

Point-cloud, Semantic segmentation, Pre-training, Semi-supervised learning

[Paper] [Codes]

Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

Cheng Sun, Min Sun, Hwann-Tzong Chen

CVPR 2022 (oral)

Grid-based NeRF

[Paper] [Paper v2] [Codes] [Project Page] [Video]

It's one of the first method to speedup NeRF optimization using grid-based models. NeRF takes 20+ hours to optimize a scene while our v2 takes only 5 minutes with comparable quality.

Specialize and Fuse: Pyramid Output Representation for Semantic Segmentation

Chi-Wei Hsiao*, Cheng Sun*, Hwann-Tzong Chen, Min Sun

ICCV 2021

Semantic segmentation


HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

Cheng Sun, Min Sun, Hwann-Tzong Chen

CVPR 2021

360 panorama, Semantic segmentation, Depth, Room layout

[Paper] [Codes] [Project Page] [Video]

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun, Hwann-Tzong Chen

CVPR 2021 (oral)

360 panorama, Planes detection, New dataset

[Paper] [Codes] [Video]

Leveraging Auxiliary Information from EMR for Weakly Supervised Pulmonary Nodule Detection

Hao-Hsiang Yang, Fu-En Wang, Cheng Sun, Kuan-Chih Huang, Hung-Wei Chen, Yi Chen, Hung-Chih Chen, Chun-Yu Liao, Shih-Hsuan Kao, Yu-Chiang Frank Wang, Chou-Jin Lan


MRI, 3D detection, Weakly-supervised learning


360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images

Shih-Han Chou, Cheng Sun, Wen-Yen Chang, Wan-Ting Hsu, Min Sun, Jianlong Fu

WACV 2020

360 panorama, Object detection, New dataset

[Paper] [Dataset] [Project Page]

Flat2Layout: Flat Representation for Estimating Layout of General Room Types

Chi-Wei Hsiao, Cheng Sun, Min Sun, Hwann-Tzong Chen

Room layout


HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation

Cheng Sun, Chi-Wei Hsiao, Min Sun, Hwann-Tzong Chen

CVPR 2019

360 panorama, Room layout, Data augmentation

[Paper] [Codes] [Project Page]

We introduced a novel 360 room layout parameterization, which is now widely adopted in this task. It won the 1st place in ECCV 2020 Holistic 3D Vision Challenge. It was also adopted as the strong baseline in Kujiale's Structure3D and Zillow's ZInD official benchmarks.

DLWV2: a Deep Learning-based Wearable Vision-system with Vibrotactile-feedback for Visually Impaired People to Reach Objects

Meng-Li Shih, Yi-Chun Chen, Chia-Yu Tung, Cheng Sun, Ching-Ju Cheng, Liwei Chan, Srenivas Varadarajan, Min Sun

IROS 2018

Object detection, HCI



PhD, EECS, National Tsing Hua University

2018 Sep - 2023 Sep (expected)

GPA – 4.28 / 4.3

Advisors: Prof. Hwann-Tzong Chen (at VLLab) and Prof. Min Sun (at VSLab).

I transformed it from an MS program to a Ph.D. program in Aug 2020.

BS, CS, National Chiao Tung University

2014 Sep - 2018 Feb

GPA – 3.87 / 4.0

It is now called National Yang Ming Chiao Tung University.


Phi Tau Phi Scholastic Honor Society Honorary Membership

Apr 2023

Awarded to students with outstanding academic performance.

Computer Vision Research Intern, Aeolus Robotics

Feb 2023 - now

Indoor 3D reconstruction from robot sensor / Generic 3D semantic and instance segmentation

Research Scientist Intern, Meta Reality Labs

June 2022 - Dec 2022

Object 3D reconstruction from RGB video / Physically-based material estimation / Lighting estimation

Google Conference Scholarship

May 2022

Thanks google for my trip from Taiwan to New Orleans.

Ph.D. Scholarship, ASUS Intelligent Cloud Services (AICS)

Sep 2020 - Apr 2022

Awarded to phd students with outstanding research ability.

Research Scientist Intern, Appier

Dec 2019 - Feb 2020

Tabular data / Clickthrough rate estimation.

M.S. Scholarship, Novatek

Aug 2019 - July 2020

Awarded to master students with outstanding research ability.

Side Projects

  • Pure python w/ numpy/scipy implmentation
  • Convertion between equirectangular and cubemap
  • Convertion from equirectangular to perspective view
Yet another SAT solver
  • 2000+ lines C/C++ codes
  • Features - Iterative DPLL, 2 Literal Watching, Nonchronological Backtracking, Learnt Clause Minimization...


I wanted to be a frontend engineer when I was a B.S. student, so I joined the open-source community in Taiwan and volunteered to create event websites. Here are some event main pages I implement with the design team: SITCON CAMP 2015, SITCON 2016, COSCUP 2016, and SITCON 2017.

I played ACM International Collegiate Programming Contest (ACM-ICPC) and competitive programming when I was undergrade. The competitors are asked to solve 5 to 13 problems in 3 to 5 hours using algorithm, data structure, math and their problem solving skill. Our team use C/C++ and achieved 8th place in 2016 Taiwan regional and 9th Place in 2016 Korean Regional. Feel free to add me as codeforces friend.

I was enthusiastic about GO game and played until senior high school, achieving amateur 2 dan in Taiwan. I sometimes play with online AI now. Feel free to add me as OGS friend.