Publications – DGIST Computer Vision Lab.

Top-tier conferences: CVPR, ICCV, ECCV, NeurIPS (NIPS), ICML, and ICLR are considered as high prestigious and top-tier conferences, which deem to have larger impacts than most SCI journals. According to Google scholar metrics, all these conferences are listed in the top 100 publications across all academic fields. Out of them, CVPR is the 2nd rank (Nature and Science are the 1st and 4th ranked respectively) among all academic fields, e.g., In terms of acceptance rate, oral presentations are about less than 4% and poster presentations about 20%, i.e., highly competitive.

Top-tier journals: IEEE TPAMI (IF: 20.8, Top 1%), IJCV (IF:11.6, Top 3%) and TIP (IF: 10.8, Top 3%) have the highest impact factors across all computer science categories.

* indicates equal contribution.
† indicates corresponding author.

Arxiv

Context-Aware Video Instance Segmentation
Seunghun Lee*, Jiwan Seo*, Kiljoon Han, Minwoo Choi, Sunghoon Im†
Arxiv, 2024
- State-of-the-Art of Video Instance Segmentation on YouTube-VIS val, YouTube-VIS 2021, OVIS val
- State-of-the-Art of Video Panoptic Segmentation on VIPSeg
[Paper] [Project page] [Code]
Scene Understanding/Video Instance Segmentation

2025

Style-Editor: Text-driven object-centric style editing
Jihun Park*, Jongmin Gim*, Kyoungmin Lee*, Seunghun Lee, Sunghoon Im†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
- Encouragement Prize, 30th HumanTech Paper Award, Samsung Electronics Co., Ltd.
[Paper]
Image Editing/Style Transfer

Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
Woo Kyoung Han, Byeonghun Lee, Hyunmin Cho, Sunghoon Im†, Kyong Hwan Jin†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[Paper]
Image Restoration

Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
Jaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon Im†
IEEE Robotics and Automation Letters (RA-L), 2025
- 1st place, LiDAR Scene Flow of Argoverse Challenge, CVPRw24
[Paper] [Code]
LiDAR Perception/Scene Flow/Autonomous Driving

Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
Wonhyeok Choi*, Kyumin Hwang*, Minwoo Choi, Kiljoon Han, Wonjoon Choi, Mingyu Shin, Sunghoon Im†
The Association for the Advancement of Artificial Intelligence (AAAI), 2025
[Paper]
3D Reconstruction/Generalization

Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining
Wonhyeok Choi*, Kyumin Hwang*, Wei Peng, Minwoo Choi, Sunghoon Im†
International Conference on Learning Representations (ICLR), 2025
- The Top Award, 16th ICT Paper Award, Electronic Newspaper
[Paper]
3D Reconstruction/Generalization

2024

Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders
Jongmin Gim*, Jihun Park*, Kyoungmin Lee*, Sunghoon Im†
Asian Conference on Computer Vision (ACCV), 2024
[Paper]
Image Editing/Style Transfer

Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains
Jaeyeul Kim*, Jungwan Woo*, Jeonghoon Kim, Sunghoon Im†
European Conference on Computer Vision (ECCV), 2024
[Paper] [Code]
LiDAR perception/Generalization/Autonomous Driving

BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow
EungGu Kang, Byeonghun Lee, Sunghoon Im†, Kyong Hwan Jin†
European Conference on Computer Vision (ECCV), 2024
[Paper] [Code]
Image Restoration

Density-aware Domain Generalization for LiDAR Semantic Segmentation
Jaeyeul Kim*, Jungwan Woo*, Ukcheol Shin, Jean Oh, Sunghoon Im†
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
[Paper]
LiDAR perception/Generalization/Autonomous Driving

JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
Woo Kyoung Han, Sunghoon Im, Jaedeok Kim, Kyong Hwan Jin†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Paper] [Project page] [Code]
Image Restoration

Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator
Wonhyeok Choi*, Mingyu Shin*, Hyukzae Lee, Jaehoon Cho, Jaehyeon Park, Sunghoon Im†
IEEE International Conference on Robotics and Automation (ICRA), 2024
- Excellence Award, 15th ICT Paper Award, Electronic Newspaper
[Paper]
Multi-task Learning/Scene Understanding/Autonomous Driving

A Study on the Generality of Neural Network Structures for Monocular Depth Estimation
Jinwoo Bae, Kyumin Hwang, Sunghoon Im†
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted
[Paper]
3D Reconstruction/Generalization/Autonomous Driving

Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction
Minsu Kim, Jaewon Lee, Byeonghun Lee, Sunghoon Im, Kyeonghwan Jin†
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
[Paper] [Code]
Implicit Neural Representation/Feature learning

Offline-to-Online Knowledge Distillation for Video Instance Segmentation
Hojin Kim, Seunghun Lee, Hyeon Kang, Sunghoon Im†
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 (Oral, Top 2.6%)
[Paper]
Scene Understanding/Video Instance Segmentation

2023

Depth-discriminative Metric Learning for Monocular 3D Object Detection
Wonhyeok Choi*, Mingyu Shin*, Sunghoon Im†
Neural Information Processing Systems (NeurIPS), 2023
- Bronze Prize, 30th HumanTech Paper Award, Samsung Electronics Co., Ltd.
[Paper] [Code]
Monocular 3D Object Detection/Metric Learning

Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation
Changjae Kim, Seunghun Lee, Sunghoon Im†
The 34th British Machine Vision Conference (BMVC), 2023
[Paper] [Poster]
Domain Adaptation/Semantic Segmentation

Rotation Matters: Generalized Monocular 3D Object Detection for Various Camera System
Sungho Moon, Jinwoo Bae, Sunghoon Im†
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2023
[Paper] [Poster]
Monocular 3D Object Detection/Generalization

Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies
Wonhyeok Choi, Sunghoon Im†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[Paper]
Multi-task Learning/Neural Architecture Search/Dynamic Neural Network

Deep Digging into the Generalization of Self-supervised Monocular Depth Estimation
Jinwoo Bae, Sungho Moon, Sunghoon Im†
Association for the Advancement of Artificial Intelligence (AAAI), 2023
[Paper]
3D Reconstruction/Generalization/Autonomous Driving

2022

LiDAR 3D Object Detection via Self-Training and Knowledge Distillation
Jungwan Woo*, Jaeyeul Kim*, Sunghoon Im†
ECCV workshop on 3D Perception for Autonomous Driving (ECCVw), Oct 2022
- Asian Federation of Computer Vision (AFCV) Best Robot Vision Paper Award, 18th Korea Robotics Society Annual Conference (KRoC)
- 3rd place, LiDAR self-supervised learning challenge, ECCVw22
LiDAR perception/Generalization/Autonomous Driving

ProFeat: Unsupervised Image Clustering via Progressive Feature Refinement
Jeonghoon Kim, Sunghoon Im, Sunghyun Cho†
Pattern Recognition Letters (PRL), 2022
CVPR workshop on Learning From Limited or Imperfect Data (CVPRw), 2021
[Paper]
Scene Understanding/Data Hungry

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon Im†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
- Encouragement Prize, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd.
[Paper] [Code]
Image Synthesis/Generalization/Autonomous Driving

CMSNet: Deep Color and Monochrome Stereo
Hae-Gon Jeon, Sunghoon Im, Jaesung Choe, Minjun Kang, Joon-Young Lee, Martial Hebert
International Journal of Computer Vision (IJCV), Jan 2022
[Paper]
3D Reconstruction/DL+Prior Knowledge/AR/VR

Facial Depth and Normal Estimation using Single Dual-Pixel Camera
Minjun Kang, Jaesung Choe, Hyowon Ha, Hae-Gon Jeon, Sunghoon Im, In So Kweon and Kuk-Jin Yoon
European Conference on Computer Vision (ECCV), Oct 2022
[Paper] [Code]
3D Reconstruction/DL+Prior Knowledge/AR/VR

RVMOS: Range-View Moving Object Segmentation Leveraged by Semantic and Motion Features
Jaeyeul Kim*, Jungwan Woo*, Sunghoon Im†
IEEE Robotics and Automation Letters (RAL), 2022
This paper was presented at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022.
[Paper]
Scene Understanding/LiDAR Perception/Autonomous Driving

Self-supervised Monocular Depth and Motion Learning in Dynamic Scenes: Semantic Prior to Rescue
Seokju Lee, Francois Rameau, Sunghoon Im, In So Kweon
International Journal of Computer Vision (IJCV), 2022
[Paper]
3D Reconstruction/Data Hungry/Autonomous Driving

2021

ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack
Dahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha Kung†
British Machine Vision Conference (BMVC), 2021
[Paper]
Adversarial Attack/Data Hungry

VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
Jaesung Choe, Sunghoon Im, François Rameau, Minjun Kang, In So Kweon
IEEE International Conference on Computer Vision (ICCV), 2021
[Paper]
3D Reconstruction/DL+Prior Knowledge/AR/VR

A Large-scale Virtual Dataset and Egocentric Localization for Disaster Responses
Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, François Rameau, Dong-Geol Choi, Jean Oh, In So Kweon, and Martial Hebert
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted
[Paper]
3D Localization/Data Hungry

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
Seunghun Lee, Sunghyun Cho, Sunghoon Im†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
- Excellence Award, 13rd ICT Paper Award, Electronic Newspaper
[Paper] [Code]
Image Synthesis/Generalization/Autonomous Driving

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
The Thirty-Fifth AAAI Conference on Artiﬁcial Intelligence (AAAI), 2021
- Best paper, Qualcomm Innovation Fellowship Korea 2020
- Silver Prize, 16th Samsung Electro-Mechanics Best Paper Awards
[Paper] [Project page] [Code]
Scene Understanding/Data Hungry/Autonomous Driving

Deep Depth from Uncalibrated Small Motion Clip
Sunghoon Im, Hyowon Ha, Hae-Gon Jeon, Stephen Lin, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Apr 2021
- Selected as Outstanding Research Achievement of GIST
[Paper]
3D Reconstruction/DL+Prior Knowledge/AR/VR

2020

Instance-wise Depth and Motion Learning from Monocular Videos
Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
Workshop on Machine Learning for Autonomous Driving (NeurIPS), 2020
Workshop on Differentiable computer vision, graphics, and physics in machine learning (NeurIPS), 2020
- Honorable Mention, 12th Electronic Times ICT Paper Contest
[Paper] [Project page]

Learning Shape-based Representation for Visual Localization in Extremely Changing Conditions
Hae-Gon Jeon, Sunghoon Im, Jean Oh, Martial Hebert
IEEE International Conference on Robotics and Automation (ICRA), 2020
[Paper]

Ring Difference Filter for Fast and Noise Robust Depth from Focus
Hae-Gon Jeon, Jaeheung Surh, Sunghoon Im, In So Kweon
IEEE Transactions Image Processing (TIP), Dec 2020
[Paper] [Code]

2019

DISC: A Large-scale Virtual Dataset for Simulating Disaster Scenarios
Hae-Gon Jeon, Sunghoon Im, Byeong-Uk Lee, Dong-Geol Choi, Martial Hebert, In So Kweon
IEEE/RSJ International Conference on Intelligence Robots and Systems (IROS), 2019
[Paper] [Project page]

Learning Residual Flow as Dynamic Motion from Stereo Video
Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
IEEE/RSJ International Conference on Intelligence Robots and Systems (IROS), 2019
[Paper] [Project page]

DPSNet: End-to-end Deep Plane Sweep Stereo
Sunghoon Im, Hae-Gon Jeon, Stephen Lin, In So Kweon
International Conference on Learning Representations (ICLR), 2019
[Paper] [Code]

Depth Completion with Deep Geometry and Context Guidance
Byeong-Uk Lee, Hae-Gon Jeon, Sunghoon Im, In So Kweon
IEEE International Conference on Robotics and Automation (ICRA), 2019
[Paper]

Robust Depth Estimation using Auto-Exposure Bracketing
Sunghoon Im, Hae-Gon Jeon, In So Kweon
IEEE Transactions Image Processing (TIP), May 2019
[Paper]

Accurate 3D Reconstruction from Small Motion Clip for Rolling Shutter Cameras
Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Apr 2019
[Paper]

~2018

RANUS: RGB and NIR Urban Scene Dataset for Deep Scene Parsing
Gyeongmin Choe, Seong-heum Kim, Sunghoon Im, Joon-Young Lee, Srinivasa Narasimhan, In So Kweon
IEEE Robotics and Automation Letters (RAL), July 2018
[Paper]

Robust Depth Estimation from Auto Bracketed Images
Sunghoon Im, Hae-Gon Jeon, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
- Best Poster Award, Samsung AI Forum 2018
[Paper]

Geometry Guided 3D Propagation for Depth from Small Motion
Seunghak Shin, Sunghoon Im, Inwook Shim, Hae-Gon Jeon, In So Kweon
IEEE Signal Processing Letters (SPL), Dec 2017
[Paper]

Noise Robust Depth from Focus using a Ring Difference Filter
Jaeheung Surh, Hae-Gon Jeon, Yunwon Park, Sunghoon Im, Hyowon Ha, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight)
[Paper] [Project page]

All-around Depth from Small Motion with A Spherical Panoramic Camera
Sunghoon Im, Hyowon Ha, Francois Rameau, Hae-Gon Jeon, Gyeongmin Choe, In So Kweon
European Conference on Computer Vision (ECCV), 2016
- Best Poster Presentation Award, 29th IPIU 2017
[Paper] [Code]

High-quality Depth from Uncalibrated Small Motion Clip
Hyowon Ha, Sunghoon Im, Jaesik Park, Hae-Gon Jeon, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral)
- Qualcomm Innovation Award, Qualcomm-KAIST Innovation Awards 2016
[Paper] [Code]

Stereo Matching with Color and Monochrome Cameras in Low-light Conditions
Hae-Gon Jeon, Joon-Young Lee, Sunghoon Im, Hyowon Ha, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
- Silver Prize, 22nd HumanTech Paper Award, Samsung Electronics Co., Ltd.
- Best Poster Presentation Award, 29th IPIU 2017
[Paper]

High Quality Structure from Small Motion for Rolling Shutter Cameras
Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon
IEEE International Conference on Computer Vision (ICCV), 2015
- Best Poster Award, IWRCV 2015
[Paper] [Code]

Depth from Accidental Motion using Geometry Prior
Sunghoon Im, Gyeongmin Choe, Hae-Gon Jeon, In So Kweon
IEEE International Conference on Image Processing (ICIP), 2015 (Top 10%)
[Paper]