Samarth Shukla

TL;DR: The first Mobile AI challenge as discussed by the authors was introduced to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms, where participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters.

TL;DR: The first Mobile AI challenge as discussed by the authors was introduced to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms.

TL;DR: The experiments show that an extremely weak supervised I2I translation solution using only one paired training sample can achieve a quantitative performance much better than the unsupervised CycleGAN model, and comparable to that of the supervised pix2pix model trained on thousands of pairs.

TL;DR: In this paper, the authors propose a method to select (very few) paired training samples and achieve significant improvements in both supervised and unsupervised I2I translation settings over random selection.

TL;DR: A trainable Image Signal Processing framework that produces DSLR quality images given RAW images captured by a smartphone is proposed, and the ISP in the Wild (ISPW) dataset is introduced, consisting of weakly paired phone RAW and DSLR sRGB images.