Towards Real-world Event-guided Low-light Video Enhancement and Deblurring- Author : Taewoo Kim, Jaeseok Jeong, Hoonhee Cho, Yuhwan Jeong, and Kuk-Jin Yoon – Published Date : TBD – Category : Low-light Video Enhancement and Deblurring – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: In low-light conditions, capturing videos with frame-based cameras often requires long…
Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation- Author : Hoyong Kwon, Jaeseok Jeong, Sung-Hoon Yoon, and Kuk-Jin Yoon – Published Date : TBD – Category : Weakly Supervised Semantic Segmentation – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Weakly Supervised Semantic Segmentation (WSSS) with image-level supervision typically acquires object…
Temporal Event Stereo via Joint Learning with Stereoscopic Flow- Author : Hoonhee Cho*, Jae-Young Kang*, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : Event Stereo – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Event cameras are dynamic vision sensors inspired by the biological retina, characterized by their high…
Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras- Author : Hoonhee Cho*, Sung-Hoon Yoon*, Hyeokjun Kweon*, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : Event Weakly Supervised Semantic Segmentation – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Event cameras excel in capturing high-contrast scenes and dynamic…
Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks- Author : Hunmin Yang, Jongoh Jeong, and Kuk-Jin Yoon – Published Date : TBD – Category : Transferable Adversarial Attacks – Place of publication : European Conference on Computer Vision (ECCV) 2024 (oral) Abstract: Recent vision-language foundation models, such as CLIP, have demonstrated superior capabilities in learning representations that can be transferable…
Diffusion-Guided Weakly Supervised Semantic Segmentation- Author : Sung-Hoon Yoon, Hoyong Kwon*, Jaeseok Jeong*, Daehee Park, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : Weakly Supervised Semantic Segmentation – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Weakly Supervised Semantic Segmentation (WSSS) with image-level supervision typically uses Class Activation Maps to…
On-the-fly Category Discovery for LiDAR Semantic Segmentation- Author : Hyeonseong Kim*, Sung-Hoon Yoon*, Minseok Kim, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : LiDAR Semantic Segmentation – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: LiDAR semantic segmentation is important for understanding the surrounding environment in autonomous driving. Existing methods…
Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach- Author : Yunseo Yang*, Jihun Kim*, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : Point Cloud Completion – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Acquiring complete point clouds for real-world scenarios is labor-intensive, making it impractical…
CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring- Author : Taewoo Kim*, Hoonhee Cho*, and Kuk-Jin Yoon – Published Date : TBD – Category : Video Deblurring – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Video deblurring aims to enhance the quality of restored results in motion-blurred videos by effectively gathering information from…
GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer- Author : Youngho Yoon*, Hyun-Kurl Jang*, and Kuk-Jin Yoon (*equal contribution) – Published Date : TBD – Category : Generalizable Neural Rendering – Place of publication : European Conference on Computer Vision (ECCV) 2024 Abstract: Novel view synthesis (NVS) aims to generate images at arbitrary viewpoints using multi-view…