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
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 |
|---|---|---|---|
| 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 -> 19.62 | Improved |
| 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 -> 6.48 | Improved |
| 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 -> 19.06 | Improved |
| 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 -> 19.62 | Improved |
| 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 -> 6.48 | Improved |
| replace Tikhonov with the proposed network (end-to-end) | FlatCam reconstruction · FlatCam display captures (100 ImageNet test images) | PSNR (dB): 10.95 -> 19.62 | Improved |
| replace Tikhonov with the proposed network (end-to-end) | FlatCam reconstruction · FlatCam display captures (100 ImageNet test images) | reconstruction time (s): 0.03 -> 0.006 | Improved |
| replace TVAL3 with the proposed network | FlatCam reconstruction · FlatCam display captures (100 ImageNet test images) | reconstruction time (s): 45.28 -> 0.006 | Improved |
| add perceptual and adversarial losses to MSE loss (ablation) | FlatCam reconstruction network · FlatCam display captures (qualitative, Fig. 4) | perceptual quality | Improved |
| replace U-Net blocks with residual blocks (ablation) | Perceptual enhancement stage · FlatCam display captures | reconstruction quality | No clear effect |
Closest papers by meaning
- FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements (TPAMI 2020 · similarity 0.94)
- PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging (NeurIPS 2024 · similarity 0.85)
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction (NeurIPS 2025 · similarity 0.83)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.83)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.83)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.82)
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.
