Sunghwan Hong

Post-doc researcher at ETH Zurich

hongsu@ethz.ch

About
I did my Ph.D. at Korea University in the Computer Vision Lab, supervised by Prof. Seungryong Kim. My PhD was focused on Computer Vision and its applications, especially in the tasks of image matching, 3D reconstruction, pose estimation and novel-view rendering. During my PhD I had the opportunity to intern in Microsft Research Asia, working with Dr. Chong Luo and Dr. Jiaolong Yang. I am one of the Google Ph.D. fellowship recipient of 2023. I worked as a postdoctoral researcher with Seungryong Kim at KAIST. Now I'm at ETH Zurich as a postdoctoral fellow, working with Prof. Dr. Marc Pollefeys, who is leading CVG, and Prof. Dr. Konrad Shindler, leading PRS.

I am always open to research collaboration. Also, if you are interested in semester projects (ETHZ) or master's theses (ETHZ) related to 2D/3D computer vision (check my CV for my research interests or see here ), feel free to contact me via email.
News
June 2026     Four papers got accepted to ECCV 2026!
May 2026     Our paper on Computer Use Agents (CUA) was accepted to ICML 2026!
Mar 2026     Three paper got accepted to CVPR 2026!
Jan 2026     One paper got accepted to ICLR 2026!
Sep 2025     Two papers got accepted to NeurIPS 2025!
May 2025     Our paper PF3plat got accepted to ICML 2025!
Feb 2025     I have been awarded the ETH AI Center Postdoctoral Fellowship!
Feb 2025     I am thrilled to share that I have officially received my Ph.D.
Feb 2025     Our paper ZeroCo got accepted to CVPR 2025!
Sep 2024     Our paper PixelCLIP got accepted to NeurIPS 2024!
Sep 2024     I will be a visiting researcher at ETH-Zurich, in CVG Group, working with Prof. Marc Pollefeys.
April 2024     Our CoPoNeRF and CAT-Seg are selected as highlights!
February 2024     Our two papers CoPoNeRF and CAT-Seg got accepted to CVPR 2024!
February 2024     Our paper CoPoNeRF got awarded (Bronze) by IPIU 2024!
January 2024     Our UFC paper got accepted to ICLR 2024!
Octobober 2023     I got awarded a Google PhD Fellowship (2023)!
Dec 2022     Our paper CATs++ got accepted to TPAMI!
October 2022     I started an internship at Microsoft Research Asia hosted by Chong Luo.
October 2022     Our paper NeMF got accepted to NeurIPS 2022!
Aug 2022     Our paper VAT got accepted to ECCV 2022!
October 2021     Our paper CATs got accepted to NeurIPS 2021!
Aug 2021     Our paper DMP got accepted to ICCV 2021!

Education

Korea University Mar. 2021 - Feb. 2025

M.S./Ph.D in Artificial Intelligence (advisor: Seungryong Kim)

Korea UniversityMar. 2015 - Feb. 2021

B.S. in Computer Science

Publications

Click any thumbnail to enlarge.  ·  * denotes equal contribution, † denotes corresponding author.

2026
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models

Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models

Marcel Gröpl*, Jaewoo Jung*, Seungryong Kim, Marc Pollefeys, Sunghwan Hong†

ECCV 2026
Paper Code
Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

Yung-Hsu Yang, Luigi Piccinelli, Samuel Rota Bulò, Sunghwan Hong, Denis Rozumny, Johannes Schönberger, Zuria Bauer, Hermann Blum, Peter Kontschieder, Marc Pollefeys

ECCV 2026
TORA: Topological Representation Alignment for 3D Shape Assembly

TORA: Topological Representation Alignment for 3D Shape Assembly

Nahyuk Lee*, Zhiang Chen*, Marc Pollefeys, Sunghwan Hong†

ECCV 2026
Paper Code
TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation

TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation

Jini Yang, Eunbeen Hong, Soowon Son, Hyunkoo Lee, Sunghwan Hong, Sunok Kim, Seungryong Kim

ECCV 2026
Paper Code
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing

ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing

A. Said Gurbuz, Sunghwan Hong†, Ahmed Nassar, Marc Pollefeys, Peter Staar

ICML 2026
Paper Code
C3G: Learning Compact 3D Representations with 2K Gaussians

C3G: Learning Compact 3D Representations with 2K Gaussians

Honggyu An*, Jaewoo Jung*, Mungyeom Kim, Chaehyun Kim, Minkyeong Jeon, Jisang Han, Kazumi Fukuda, Takuya Narihira, Hyunah Ko, Junsu Kim, Sunghwan Hong†, Yuki Mitsufuji†, Seungryong Kim†

CVPR 2026
Paper Code
Emergent Outlier View Rejection in Visual Geometry Grounded Transformers

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers

Jisang Han*, Sunghwan Hong*, Jaewoo Jung, Wooseok Jang, Honggyu An, Qianqian Wang, Seungryong Kim, Chen Feng

CVPR 2026
Paper Code
LitePT: Lighter Yet Stronger Point Transformer

LitePT: Lighter Yet Stronger Point Transformer

Yuanwen Yue, Damien Robert, Jianyuan Wang, Sunghwan Hong, Jan Dirk Wegner, Christian Rupprecht, Konrad Schindler

CVPR 2026 (Highlight)
Paper Code
3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

JoungBin Lee*, Jaewoo Jung*, Jisang Han*, Takuya Narihira, Kazumi Fukuda, Junyoung Seo, Sunghwan Hong, Yuki Mitsufuji†, Seungryong Kim†

ICLR 2026
Paper Code
LIME: Learning Intent-aware Camera Motion from Egocentric Video

LIME: Learning Intent-aware Camera Motion from Egocentric Video

Boyang Sun, Jiajie Li, Yung-Hsu Yang, Chenyangguang Zhang, Tim Engelbracht, Sunghwan Hong, Cesar Cadena, Marc Pollefeys, Hermann Blum

Arxiv 2026
Paper Code
Geometric Action Model for Robot Policy Learning

Geometric Action Model for Robot Policy Learning

Jisang Han, Seonghu Jeon, Jaewoo Jung, René Zurbrügg, Honggyu An, Tifanny Portela, Marco Hutter, Marc Pollefeys, Seungryong Kim, Sunghwan Hong†

Arxiv 2026
Paper Code
PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models

PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models

Zhiang Chen, Nahyuk Lee, Boyang Sun, Taein Kwon, Marc Pollefeys, Zuria Bauer, Sunghwan Hong†

Arxiv 2026
Paper Code
ZipSplat: Fewer Gaussians, Better Splats

ZipSplat: Fewer Gaussians, Better Splats

Alexander Veicht, Sunghwan Hong†, Dániel Baráth, Marc Pollefeys

Arxiv 2026
Paper Code
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction

Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction

Mungyeom Kim, Minkyeong Jeon, Honggyu An, Jaewoo Jung, Hyuna Ko, Jisang Han, Hyeonseo Yu, Donghwan Shin, Sunghwan Hong, Takuya Narihira, Kazumi Fukuda, Yuki Mitsufuji, Seungryong Kim

Arxiv 2026
Paper Code
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

Matteo Balice, Yanik Künzi, Chenyangguang Zhang, Matteo Matteucci, Marc Pollefeys, Sunghwan Hong†

Arxiv 2026
Paper Code
VIRAL: Visual Representation Alignment for Multimodal Large Language Models

VIRAL: Visual Representation Alignment for Multimodal Large Language Models

Heeji Yoon*, Jaewoo Jung*, Junwan Kim*, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim

Arxiv 2026
Paper Code
2025
D2USt3R: Enhancing 3D Reconstruction for Dynamic Scenes

D2USt3R: Enhancing 3D Reconstruction for Dynamic Scenes

Jisang Han*, Honggyu An*, Jaewoo Jung*, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji†, Seungryong Kim†

NeurIPS 2025
Paper Code
Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong†, Seungryong Kim†

NeurIPS 2025
Paper Code
PF3plat : Pose-Free Feed-Forward 3D Gaussian Splatting

PF3plat : Pose-Free Feed-Forward 3D Gaussian Splatting

Sunghwan Hong*, Jaewoo Jung*, Heeseong Shin, Jisang Han, Jiaolong Yang†, Chong Luo†, Seungryong Kim†

ICML 2025
Paper Code
Cross-View Completion Models are Zero-shot Correspondence Estimators

Cross-View Completion Models are Zero-shot Correspondence Estimators

Honggyu An*, Jinhyeon Kim*, Seonghoon Park, Jaewoo Jung, Jisang Han, Sunghwan Hong†, Seungryong Kim†

CVPR 2025 (Highlight)
Paper Code
2024
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Heeseong Shin, Chaehyon Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim

NeurIPS 2024
Paper Code
Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs

Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs

Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang, Seungryong Kim, Chong Luo

CVPR 2024 (Highlight)
Paper Code
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

Seokju Cho*, Heeseong Shin*, Sunghwan Hong, Anurag Arnab, Paul Hongseok Seo, Seungryong Kim

CVPR 2024 (Highlight)
Paper Code
Unifying Feature and Cost Aggregation with Transformers for Dense Correspondence

Unifying Feature and Cost Aggregation with Transformers for Dense Correspondence

Sunghwan Hong*, Seokju Cho*, Seungryong Kim, Stephen Lin

ICLR 2024
Paper
2023
CATs++: Boosting Cost Aggregation with Convolutions and Transformers

CATs++: Boosting Cost Aggregation with Convolutions and Transformers

Seokju Cho*, Sunghwan Hong*, Seungryong Kim

TPAMI
Paper Code
2022
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, Seungryong Kim

NeurIPS 2022
Paper Code
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Sunghwan Hong*, Seokju Cho*, Jisu Nam, Stephen Lin, Seungryong Kim

ECCV 2022
Paper Code
2021
CATs: Cost Aggregation Transformers for Visual Correspondence

CATs: Cost Aggregation Transformers for Visual Correspondence

Seokju Cho*, Sunghwan Hong*, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn, Seungryong Kim

NeurIPS 2021
Paper Code
Deep Matching Prior: Test-Time Optimization for Dense Correspondence

Deep Matching Prior: Test-Time Optimization for Dense Correspondence

Sunghwan Hong, Seungryong Kim

ICCV 2021
Paper Code
( * indicates equal contribution and † indicates corresponding author )

Vitæ

Full CV in PDF.

  • ETH AI Center July 2025 - Present
    Postdoctoral Researcher
  • KAIST CVLAB Mar. 2025 - June 2025
    Postdoctoral Researcher
  • ETH-Zurich CVG Group Sep 2024 - Feb 2025
    Visiting Researcher
    Working on Robotics/Vision Foundation Model
  • Microsoft Research Asia Oct 2023 - Apr 2024
    Research Intern (Mentors: Chong Luo)
    Working on 3D Vision
  • Korea University Mar. 2021 - Feb. 2025
    M.S./Ph.D Student (Advisor: Seungryong Kim)
  • Korea National Forensic Service Jan. 2020 - June. 2020
    Research Assistant
    Worked on a national project for AI-based forensic analysis
  • Korea National Police Agency Jul. 2016 - Apr. 2018
    Auxiliary Police
    Carried out obligatory duty of national defense
  • Korea University Mar. 2015 - Feb. 2021
    B.S. in Computer Science
Sunghwan Hong
Last updated on August 7, 2026