AI Paper Atlas

Research map / Image generation / Image restoration

Towards Photorealistic Reconstruction of Highly Multiplexed Lensless Images

Salman S. Khan, Adarsh V. R., Vivek Boominathan, Jasper Tan, Ashok Veeraraghavan, Kaushik Mitra

ICCV 2019 · Image generation › Image restoration · approach: Image harmonization and color transformation · 36 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
add trainable inversion stage in place of Tikhonov pre-reconstruction (naive approach) (ablation)FlatCam reconstruction network (transpose init) · FlatCam display captures (100 ImageNet test images)PSNR (dB): 18.90 -> 19.62Improved
add trainable inversion stage in place of Tikhonov pre-reconstruction (naive approach) (ablation)FlatCam reconstruction network (transpose init) · FlatCam display captures (100 ImageNet test images)perceptual score (Ma et al.): 5.72 -> 6.48Improved
add trainable inversion stage in place of Tikhonov pre-reconstruction (naive approach) (ablation)FlatCam reconstruction network (random init) · FlatCam display captures (100 ImageNet test images)PSNR (dB): 18.90 -> 19.06Improved
use transpose initialization from calibration instead of calibration-free random initialization (ablation)FlatCam reconstruction network · FlatCam display captures (100 ImageNet test images)PSNR (dB): 19.06 -> 19.62Improved
use transpose initialization instead of random initialization (ablation)FlatCam reconstruction network · FlatCam display captures (100 ImageNet test images)perceptual score (Ma et al.): 5.86 -> 6.48Improved
replace Tikhonov with the proposed network (end-to-end)FlatCam reconstruction · FlatCam display captures (100 ImageNet test images)PSNR (dB): 10.95 -> 19.62Improved
replace Tikhonov with the proposed network (end-to-end)FlatCam reconstruction · FlatCam display captures (100 ImageNet test images)reconstruction time (s): 0.03 -> 0.006Improved
replace TVAL3 with the proposed networkFlatCam reconstruction · FlatCam display captures (100 ImageNet test images)reconstruction time (s): 45.28 -> 0.006Improved
add perceptual and adversarial losses to MSE loss (ablation)FlatCam reconstruction network · FlatCam display captures (qualitative, Fig. 4)perceptual qualityImproved
replace U-Net blocks with residual blocks (ablation)Perceptual enhancement stage · FlatCam display capturesreconstruction qualityNo clear effect

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