대학원소개

논문성과

CM Lab's (Prof. Jihyong Oh) paper accepted to CVPR 2024 (AI Top-tier Conference)

관리자 │ 2024-02-28

HIT

34878


Our paper of Creative Vision and Multimedia Lab (CMLab) is accepted to Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Top Conference in AI & Computer Vision [LINK]


Title: 

FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring


Authors:

Geunhyuk Youk, Jihyong Oh, Munchurl Kim


Abstract: 

We present a joint learning scheme of video super-resolution and deblurring, called VSRDB, to restore clean high-resolution (HR) videos from blurry low-resolution (LR) ones. This joint restoration problem has drawn much less attention compared to single restoration problems. We propose a novel flow-guided dynamic filtering (FGDF) and iterative feature refinement with multi-attention (FRMA), which constitutes our VSRDB framework, denoted as FMA-Net. Specifically, our proposed FGDF enables precise estimation of both spatio-temporally-variant degradation and restoration kernels that are aware of motion trajectories through sophisticated motion representation learning. Compared to conventional dynamic filtering, the FGDF enables the FMA-Net to effectively handle large motions into the VSRDB. Additionally, the stacked FRMA blocks trained with our novel temporal anchor (TA) loss, which temporally anchors and sharpens features, refine features in a course-to-fine manner through iterative updates. Extensive experiments demonstrate the superiority of the proposed FMA-Net over state-of-the-art methods in terms of both quantitative and qualitative quality.



이전글 VI Lab's (Prof. Jongwon Choi) two papers accepted to CVPR 2024 (AI Top-tier Conf...
다음글 IRIS Lab's (Prof. Hak Gu Kim) papers accepted to ICIP 2024