Research map / 3D vision / Depth and stereo
DC2: Dual-Camera Defocus Control by Learning To Refocus
Hadi Alzayer, Abdullah Abuolaim, Leung Chun Chan, Yang Yang, Ying Chen Lou, Jia-Bin Huang, Abhishek Kar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use the dual-camera DC² system rather than DRBNet | Defocus deblurring · Defocus deblurring | PSNR: 24.27 -> 24.79 | Improved |
| Use the dual-camera DC² system rather than IFAN | Defocus deblurring · Defocus deblurring | SSIM: 0.679 -> 0.704 | Improved |
| Use the dual-camera DC² system rather than IFAN | Defocus deblurring · Defocus deblurring | LPIPS: 0.371 -> 0.351 | Improved |
| Use DC² instead of Neural Rend. | Shallow DoF rendering · Shallow DoF rendering | PSNR: 27.87 -> 29.78 | Improved |
| Use DC² instead of BokehMe | Shallow DoF rendering · Shallow DoF rendering | LPIPS: 0.241 -> 0.172 | Improved |
| Refocus directly with DC² rather than deblur and reblur | Image refocus · Image refocus | PSNR: 26.40 -> 28.58 | Improved |
| Refocus directly with DC² rather than deblur and reblur | Image refocus · Image refocus | LPIPS: 0.312 -> 0.217 | Improved |
| Add the ultra-wide input to the wide-camera input (ablation) | DC² · Image refocus | PSNR: 28.44 -> 28.58 | Improved |
| Use the wide-camera input alongside the ultra-wide input (ablation) | DC² · Image refocus | PSNR: 22.66 -> 28.58 | Improved |
| Remove the occlusion mask (ablation) | DC² · Image refocus | PSNR: 28.58 -> 28.81 | Mixed |
| Use the occlusion mask (ablation) | DC² · Image refocus | LPIPS: 0.219 -> 0.217 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BokehMe — BokehMe: When Neural Rendering Meets Classical Rendering (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- User-Instructed Disparity-aware Defocus Control (NeurIPS 2025 · similarity 0.89)
- Learning To Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data (ICCV 2021 · similarity 0.88)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · similarity 0.86)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.84)
- DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal (CVPR 2025 · similarity 0.84)
- EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams (ICML 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.
