Research map / Video / Video segmentation and tracking
Asymmetric Dual-Lens Video Deblurring
Zeyu Xiao, Xinchao Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a video deblurring approach that exploits asymmetric dual-lens smartphone inputs (blurred wide lens plus sharper ultra-wide lens) as complementary cues.
Problem
Video deblurring from smartphones with asymmetric dual-lens systems, where the wide-angle lens is blurred by motion while the lower-resolution ultra-wide lens retains sharper detail; existing methods handle only single-camera or symmetric stereo inputs.
Approach
Leverages the complementary perspectives and details of the asymmetric wide and ultra-wide lens pair to guide deblurring of the wide-angle video, rather than relying on single-camera or symmetric stereo setups.
Closest papers by meaning
- Unconstrained Motion Deblurring for Dual-Lens Cameras (ICCV 2019 · similarity 0.90)
- A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention (ECCV 2026 · similarity 0.87)
- ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring (CVPR 2021 · similarity 0.86)
- Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring (AAAI 2025 · similarity 0.85)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.85)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
