Our paper has been accepted to IJCV

Self-supervised Monocular Depth and Motion Learning in Dynamic Scenes: Semantic Prior to RescueSeokju Lee, Francois Rameau, Sunghoon Im, In So KweonInternational Journal of Computer Vision (IJCV), Accepted

Our paper has been accepted to CVPR

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic SegmentationSeunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon ImIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Article …

One paper has been accepted to BMVC

ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip AttackDahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha KungBritish Machine Vision Conference (BMVC), 2021

One paper has been accepted to ICCV

VolumeFusion: Deep Depth Fusion for 3D Scene ReconstructionJaesung Choe, Sunghoon Im, François Rameau, Minjun Kang, In So KweonIEEE International Conference on Computer Vision (ICCV), 2021

Our paper has been accepted to TPAMI

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 …

Seunghun’s paper has been accepted to CVPR

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain AdaptationSeunghun Lee, Sunghyun Cho, Sunghoon ImIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Article : http://www.aitimes.com/news/articleView.html?idxno=139612

Our paper has been accepted to AAAI

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection ConsistencySeokju Lee, Sunghoon Im, Stephen Lin, In So KweonThe Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021

Our paper has been accepted to NeurIPS Workshops

Instance-wise Depth and Motion Learning from Monocular VideosSeokju Lee, Sunghoon Im, Stephen Lin, In So KweonWorkshop on Machine Learning for Autonomous Driving (NeurIPS), 2020Workshop on Differentiable computer vision, graphics, and physics …