Public

Coded Exposure / Flutter Shutter — Public Tier

(5 scenes)

Full-access development tier with all data visible.

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

Reconstructed signals (x_hat) and corrected spec as HDF5.

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter	Spec Range	True Value	Unit
shutter_code_timing_error	-1.0 – 2.0	0.5	-
motion_blur_psf_mismatch	-4.0 – 8.0	2.0	velocityerror
sensor_readout_noise	3.0 – 9.0	6.0	e-

Method: CPU_baseline — Mismatch parameter: nominal

7.84 dB

SSIM 0.3015

7.84 dB

SSIM 0.1991

10.94 dB

SSIM 0.3682

Per-scene breakdown (4 scenes)

Scene	PSNR I	SSIM I	PSNR II	SSIM II	PSNR III	SSIM III
scene_00	7.64	0.2894	7.66	0.2019	10.79	0.3739
scene_01	7.65	0.3040	7.65	0.1960	10.77	0.3632
scene_02	8.07	0.3073	8.08	0.2002	11.17	0.3690
scene_03	8.02	0.3052	7.95	0.1985	11.04	0.3666

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DiffusionDeblur + gradient	0.844	37.35	0.98	0.89	✓ Certified	Whang et al., CVPR 2022
2	Restormer-Deblur + gradient	0.829	36.17	0.974	0.89	✓ Certified	Zamir et al., CVPR 2022
3	MPRNet + gradient	0.816	35.03	0.968	0.89	✓ Certified	Zamir et al., CVPR 2021
4	DMPHN + gradient	0.798	33.49	0.957	0.9	✓ Certified	Zhang et al., CVPR 2019
5	DeblurGAN + gradient	0.783	32.86	0.951	0.87	✓ Certified	Kupyn et al., CVPR 2018
6	DnCNN-Deblur + gradient	0.760	30.71	0.927	0.91	✓ Certified	Zhang et al., IEEE TIP 2017
7	BM3D-Deblur + gradient	0.732	28.96	0.9	0.91	✓ Certified	Danielyan et al., IEEE TIP 2012
8	TV-Deconv + gradient	0.686	26.64	0.849	0.9	✓ Certified	Rudin et al., Physica D 1992
9	Wiener-Deconv + gradient	0.626	24.02	0.769	0.89	✓ Certified	Wiener, MIT Tech. Rep. 1942

y H_ideal spec_ranges x_true true_spec

Format: HDF5

Scenes: 5

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%