L
Liang Shen
Researcher at Qualcomm
Publications - 13
Citations - 634
Liang Shen is an academic researcher from Qualcomm. The author has contributed to research in topics: Multispectral image & Image restoration. The author has an hindex of 10, co-authored 12 publications receiving 528 citations.
Papers
More filters
Proceedings ArticleDOI
Cross-Field Joint Image Restoration via Scale Map
TL;DR: A scale map is introduced as a competent representation to explicitly model derivative-level confidence and new functions and a numerical solver are proposed to effectively infer it following new structural observations.
Proceedings ArticleDOI
Near-infrared guided color image dehazing
TL;DR: An improved image dehazing scheme using a pair of color and NIR images, which effectively estimates the airlight color and transfers details from the NIR, and can achieve substantial improvements on the detail recovery and the color distribution over the existing imageDehazing algorithms.
Proceedings ArticleDOI
A Quantization-Friendly Separable Convolution for MobileNets
TL;DR: Zhang et al. as mentioned in this paper proposed a quantization-friendly separable convolution architecture, which can effectively offload GPU and make it possible to deploy DL on fixed-point pipeline.
Patent
Multispectral eye analysis for identity authentication
TL;DR: In this article, the authors proposed a method for generating high resolution iris templates and detecting spoofs, enabling more reliable and secure iris authentication using RGB and NIR images.
Proceedings ArticleDOI
A Quantization-Friendly Separable Convolution for MobileNets
TL;DR: This work analyzed the root cause of quantization loss and proposed a quantization-friendly separable convolution architecture that can archive 8-bit inference top-1 accuracy and almost closed the gap to the float pipeline.