Timezone: »

Neural Proximal Gradient Descent for Compressive Imaging
Morteza Mardani · Qingyun Sun · David Donoho · Vardan Papyan · Hatef Monajemi · Shreyas Vasanawala · John Pauly

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #127

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the repetitive application of alternating proximal and data fidelity constraints. We learn a proximal map that works well with real images based on residual networks with recurrent blocks. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled k-space data and (b) super-resolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block (10-fold repetition) yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.

Author Information

Morteza Mardani (Stanford University)
Qingyun Sun (Stanford university)
David Donoho (Stanford University)
Vardan Papyan (Stanford University)
Hatef Monajemi (Stanford University)
Shreyas Vasanawala (Stanford University)
John Pauly (Stanford University)