Deep Learning

Neural Sensors: Learning Pixel Exposures for HDR Imaging and Video Compressive Sensing with Programmable Sensors

We propose the learning of the pixel exposures of a sensor, taking into account its hardware constraints, jointly with decoders to reconstruct HDR images and high-speed videos from coded images.

Implicit Neural Representations with Periodic Activation Functions

An implicitly defined neural signal representation for images, audio, shapes, and wavefields.

ICCP 2020 Neural Sensors

This is the oral presentation of our Neural Sensor paper that got accepted at ICCP'20 in the T-PAMI journal track.