Research map / 3D vision / Depth and stereo
DAVANet: Stereo Deblurring With View Aggregation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add stereo depth awareness and view aggregation | DeblurNet · Stereo Blur Dataset | PSNR: 31.97 -> 33.19 | Helped |
| Add stereo depth awareness and view aggregation | DeblurNet · Stereo Blur Dataset | SSIM: 0.9507 -> 0.9586 | Helped |
| Use a Context Module instead of a one-path convolution block (ablation) | DAVANet · Stereo Blur Dataset | PSNR: 31.40 -> 33.19 | Helped |
| Use a Context Module instead of a one-path convolution block (ablation) | DAVANet · Stereo Blur Dataset | SSIM: 0.9461 -> 0.9586 | Helped |
| Add disparity supervision and depth information (ablation) | DAVANet · Stereo Blur Dataset | PSNR: 32.69 -> 33.19 | Helped |
| Add disparity supervision and depth information (ablation) | DAVANet · Stereo Blur Dataset | SSIM: 0.9569 -> 0.9586 | Helped |
| Add view aggregation from the other stereo view (ablation) | DAVANet · Stereo Blur Dataset | PSNR: 32.53 -> 33.19 | Helped |
| Add view aggregation from the other stereo view (ablation) | DAVANet · Stereo Blur Dataset | SSIM: 0.9558 -> 0.9586 | Helped |
| Use DeblurNet with its Context Module | DeblurNet · GOPRO | PSNR: 30.26 -> 30.55 | Helped |
| Use DeblurNet with its Context Module | DeblurNet · GOPRO | SSIM: 0.9342 -> 0.9400 | Helped |
Closest papers by meaning
- Simultaneous Stereo Video Deblurring and Scene Flow Estimation (CVPR 2017 · similarity 0.88)
- K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring (CVPR 2023 · similarity 0.86)
- LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network (CVPR 2024 · similarity 0.85)
- Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing (CVPR 2024 · similarity 0.84)
- A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding (NeurIPS 2024 · similarity 0.84)
- DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025 · similarity 0.83)
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.