Changil Kim

Changil Kim

I am a Research Scientist at Meta, where I work on a variety of research problems at the intersection of computer graphics, vision, and machine learning. Previously, I was a postdoctoral fellow at MIT CSAIL and ETH Zurich in Switzerland. I received a PhD in Computer Science from ETH in collaboration with Disney Research.

I received the Swiss National Science Foundation Postdoctoral Fellowship, the Sony Focused Research Award, and the credits in Disney movies for the work I did on 3D scene reconstruction.

Email: changil@csail.mit.edu | Google Scholar

Publications

Taming Latent Diffusion Model for Neural Radiance Field Inpainting
Chieh Hubert Lin, Changil Kim, Jia-Bin Huang, Qinbo Li, Chih-Yao Ma, Johannes Kopf, Ming-Hsuan Yang, Hung-Yu Tseng
ECCV 2024
Project Page | Paper

Modeling Ambient Scene Dynamics for Free-view Synthesis
Meng-Li Shih, Jia-Bin Huang, Changil Kim, Rajvi Shah, Johannes Kopf, Chen Gao
SIGGRAPH 2024
Project Page | Paper

IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
Zhi-Hao Lin, Jia-Bin Huang, Zhengqin Li, Zhao Dong, Christian Richardt, Tuotuo Li, Michael Zollhöfer, Johannes Kopf, Shenlong Wang, Changil Kim
ArXiv, 2024
Project Page | Paper

LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering
Jaehoon Choi, Rajvi Shah, Qinbo Li, Yipeng Wang, Ayush Saraf, Changil Kim, Jia-Bin Huang, Dinesh Manocha, Suhib Alsisan, Johannes Kopf
CVPR 2024
Project Page | Paper | Video

TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandraker, Carl S Marshall, Zhao Dong, Zhengqin Li
CVPR 2024
Project Page | Paper | Video

SpecNeRF: Gaussian Directional Encoding for Specular Reflections
Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim, Chen Gao, Pedro V. Sander, Michael Zollhöfer, Christian Richardt
CVPR 2024
Project Page | Paper | Video

Human-SGD: Single-Image 3D Human Digitization with Shape-Guided Diffusion
Badour AlBahar, Shunsuke Saito, Hung-Yu Tseng, Changil Kim, Johannes Kopf, Jia-Bin Huang
SIGGRAPH Asia 2023
Project Page | Paper | Video

VR-NeRF: High-Fidelity Virtualized Walkable Spaces
Linning Xu, Vasu Agrawal, William Laney, Tony Garcia, Aayush Bansal, Changil Kim, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Aljaž Božič, Dahua Lin, Michael Zollhöfer, Christian Richardt
SIGGRAPH Asia 2023
Project Page | Paper | Dataset | Video

OmnimatteRF: Robust Omnimatte with 3D Background Modeling
Geng Lin, Chen Gao, Jia-Bin Huang, Changil Kim, Yipeng Wang, Matthias Zwicker, Ayush Saraf
ICCV 2023
Project Page | Paper | Dataset | Code

HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Benjamin Attal, Jia-Bin Huang, Christian Richardt, Johannes Kopf, Michael Zollhöfer, Matthew O'Toole, Changil Kim
CVPR 2023, Highlight
Project Page | Paper | Video | Supplemental Results | Code

Progressively Optimized Local Radiance Fields for Robust View Synthesis
Andreas Meuleman, Yu-Lun Liu, Chen Gao, Jia-Bin Huang, Changil Kim, Min H. Kim, Johannes Kopf
CVPR 2023
Project Page | Paper | Video | Dataset | Code

Robust Dynamic Radiance Fields
Yu-Lun Liu, Chen Gao, Andreas Meuleman, Hung-Yu Tseng, Ayush Saraf, Changil Kim, Yung-Yu Chuang, Johannes Kopf, Jia-Bin Huang
CVPR 2023
Project Page | Paper | Video | Code

Consistent View Synthesis with Pose-Guided Diffusion Models
Hung-Yu Tseng, Qinbo Li, Changil Kim, Suhib Alsisan, Jia-Bin Huang, Johannes Kopf
CVPR 2023
Project Page | Paper | Video

Neural compression for hologram images and videos
Liang Shi, Richard Webb, Lei Xiao, Changil Kim, Changwon Jang
Optics Letters 2022
Paper | Supplemental Document | BibTeX

Learning Neural Light Fields with Ray-Space Embedding Networks
Benjamin Attal, Jia-Bin Huang, Michael Zollhöfer, Johannes Kopf, Changil Kim
CVPR 2022
Paper | Video | Code | Supplemental Results | BibTeX | Project Page

Boosting View Synthesis with Residual Transfer
Xuejian Rong, Jia-Bin Huang, Ayush Saraf, Changil Kim, Johannes Kopf
CVPR 2022
Paper | Video | BibTeX | Project Page

Neural 3D Video Synthesis from Multi-view Video
Tianye Li*, Mira Slavcheva*, Michael Zollhoefer, Simon Green, Christoph Lassner, Changil Kim, Tanner Schmidt, Steven Lovegrove, Michael Goesele, Richard Newcombe, Zhaoyang Lv (*equal contributions)
CVPR 2022, Oral
Paper | Video | Data | BibTeX | Project Page

TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
Benjamin Attal, Eliot Laidlaw, Aaron Gokaslan, Changil Kim, Christian Richardt, James Tompkin, Matthew O'Toole
NeurIPS 2021
Paper | Code | BibTeX | Project Page

Towards Real-time Photorealistic 3D Holography with Deep Neural Networks
Liang Shi, Beichen Li, Changil Kim, Petr Kellnhofer, Wojciech Matusik
Nature 2021
Paper | Video | BibTeX | Project Page

AMICO: Amodal Instance Composition
Peiye Zhuang, Jia-Bin Huang, Ayush Saraf, Xuejian Rong, Changil Kim, Denis Demandolx
BMVC 2021
Paper | Talk | BibTeX

Space-time Neural Irradiance Fields for Free-Viewpoint Video
Wenqi Xian, Jia-Bin Huang, Johannes Kopf, Changil Kim
CVPR 2021
Paper | Video | BibTeX | Project Page

Speech2Face: Learning the Face Behind a Voice
Tae-Hyun Oh*, Tali Dekel*, Changil Kim*, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Wojciech Matusik (*equal contributions)
CVPR 2019
Paper | Supplement | BibTeX | Project

On Learning Associations of Faces and Voices
Changil Kim, Hijung Valentina Shin, Tae-Hyun Oh, Alexandre Kaspar, Mohamed Elgharib, Wojciech Matusik
ACCV 2018
Paper | Code | BibTeX | Project & Datasets

Deep Multispectral Painting Reproduction via Multi-layer, Custom-Ink Printing
Liang Shi, Vahid Babaei, Changil Kim, Michael Foshey, Yuanming Hu, Pitchaya Sitthi-amorn, Szymon Rusinkiewicz, Wojciech Matusik
SIGGRAPH Asia 2018
Paper | Supplement | Video | BibTeX | Datasets & Project | Press

Learning-based Video Motion Magnification
Tae-Hyun Oh*, Ronnachai Jaroensri*, Changil Kim, Mohamed Elgharib, Frédo Durand, William T. Freeman, Wojciech Matusik (*equal contributions)
ECCV 2018, Oral
Paper | Video | Code | Datasets | BibTeX | Project

A Dataset of Flash and Ambient Illumination Pairs from the Crowd
Yağız Aksoy, Changil Kim, Petr Kellnhofer, Sylvain Paris, Mohamed Elgharib, Marc Pollefeys, Wojciech Matusik
ECCV 2018
Paper | Datasets | BibTeX | Project

Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?
Alexandre Kaspar, Geneviève Patterson, Changil Kim, Yağız Aksoy, Wojciech Matusik, Mohamed Elgharib
CHI 2018
Paper | Supplement | Video | BibTeX | Project

Video Reflection Removal Through Spatio-Temporal Optimization
Ajay Nandoriya, Mohamed Elgharib, Changil Kim, Mohamed Hefeeda, Wojciech Matusik
ICCV 2017
Paper | Video | BibTeX

Depth from Gradients in Dense Light Fields for Object Reconstruction
Kaan Yücer, Changil Kim, Alexander Sorkine-Hornung, Olga Sorkine-Hornung
3DV 2016, Oral, Best Paper Award
Paper | Paper (low resolution) | Supplement | Supplement (low resolution) | Video | Datasets | BibTeX | Project

Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction
Katja Wolff, Changil Kim, Henning Zimmer, Christopher Schroers, Mario Botsch, Olga Sorkine-Hornung, Alexander Sorkine-Hornung
3DV 2016
Paper | Paper (low resolution) | Supplement | Supplement (low resolution) | Video | BibTeX | Project

3D Reconstruction and Rendering from High Resolution Light Fields
Changil Kim
PhD Thesis, ETH Zurich, 2015
Thesis | Thesis (low resolution) | BibTeX

Online View Sampling for Estimating Depth from Light Fields
Changil Kim, Kartic Subr, Kenny Mitchell, Alexander Sorkine-Hornung, Markus Gross
ICIP 2015, Oral, Top 10%
Paper | BibTeX | Project

Memory Efficient Stereoscopy from Light Fields
Changil Kim, Ulrich Müller, Henning Zimmer, Yael Pritch, Alexander Sorkine-Hornung, Markus Gross
3DV 2014, Oral
Paper | Paper (low resolution) | Supplement | Supplement (low resolution) | BibTeX | Project

Scene Reconstruction from High Spatio-Angular Resolution Light Fields
Changil Kim, Henning Zimmer, Yael Pritch, Alexander Sorkine-Hornung, Markus Gross
SIGGRAPH 2013
Paper | Paper (low resolution) | Supplement | Supplement (low resolution) | Video | Video (YouTube) | BibTeX | Project & Datasets | Press

Scalable Music: Automatic Music Retargeting and Synthesis
Simon Wenner, Jean-Charles Bazin, Alexander Sorkine-Hornung, Changil Kim, Markus Gross
Eurographics 2013
Paper | Video | BibTeX | Project

Multi-Perspective Stereoscopy from Light Fields
Changil Kim, Alexander Hornung, Simon Heinzle, Wojciech Matusik, Markus Gross
SIGGRAPH Asia 2011, Featured on ACM TOG Back Cover
Paper | Paper (low resolution) | Video | BibTeX | Project

Scene Reconstruction from a Light Field
Changil Kim
Master Thesis, ETH Zurich, 2010
Thesis | Thesis (low resolution) | BibTeX

Teaching

6.839 Advanced Computer Graphics, Co-instructor, MIT, Autumn 2018

Computer Graphics, Co-instructor, ETH Zurich, Autumn 2015
Computer Graphics, TA, ETH Zurich, Autumn 2014
Computer Graphics, TA, ETH Zurich, Autumn 2013
Computer Graphics, TA, ETH Zurich, Autumn 2012
Computer Graphics, TA, ETH Zurich, Autumn 2011

Advanced Topics in Computer Graphics and Vision, Co-instructor, ETH Zurich, Autumn 2015

Informatik I, TA, ETH Zurich, Spring 2014
Informatik I, TA, ETH Zurich, Spring 2013
Informatik I, TA, ETH Zurich, Spring 2012

Design of Digital Circuits, TA, ETH Zurich, Spring 2011

Last update: October 2024