AI Paper Atlas

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

CVPR 2023 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use the dual-camera DC² system rather than DRBNetDefocus deblurring · Defocus deblurringPSNR: 24.27 -> 24.79Improved
Use the dual-camera DC² system rather than IFANDefocus deblurring · Defocus deblurringSSIM: 0.679 -> 0.704Improved
Use the dual-camera DC² system rather than IFANDefocus deblurring · Defocus deblurringLPIPS: 0.371 -> 0.351Improved
Use DC² instead of Neural Rend.Shallow DoF rendering · Shallow DoF renderingPSNR: 27.87 -> 29.78Improved
Use DC² instead of BokehMeShallow DoF rendering · Shallow DoF renderingLPIPS: 0.241 -> 0.172Improved
Refocus directly with DC² rather than deblur and reblurImage refocus · Image refocusPSNR: 26.40 -> 28.58Improved
Refocus directly with DC² rather than deblur and reblurImage refocus · Image refocusLPIPS: 0.312 -> 0.217Improved
Add the ultra-wide input to the wide-camera input (ablation)DC² · Image refocusPSNR: 28.44 -> 28.58Improved
Use the wide-camera input alongside the ultra-wide input (ablation)DC² · Image refocusPSNR: 22.66 -> 28.58Improved
Remove the occlusion mask (ablation)DC² · Image refocusPSNR: 28.58 -> 28.81Mixed
Use the occlusion mask (ablation)DC² · Image refocusLPIPS: 0.219 -> 0.217Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy