• Publications
  • Influence
Defocus map estimation from a single image
Cross-Field Joint Image Restoration via Scale Map
TLDR
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.
Robust flash deblurring
TLDR
A novel method to recover a sharp image from a pair of motion blurred and flash images, consecutively captured using a hand-held camera is proposed, leading to an accurate blur kernel and a reconstructed image with fine image details.
Semantic colorization with internet images
TLDR
A colorization system that leverages the rich image content on the internet and the user needs only to provide a semantic text label and segmentation cues for major foreground objects in the scene to achieve the desired result.
Correcting over-exposure in photographs
TLDR
This paper introduces a method to correct over-exposure in an existing photograph by recovering the color and lightness separately, which is fully automatic and requires only one single input photo.
Enhancing low light images using near infrared flash images
TLDR
A new method to denoise an visible image and enhance its details using its corresponding NIR flash image is introduced, which shows the superiority of this method compared with previous image denoising and detail enhancement methods.
Near-infrared guided color image dehazing
TLDR
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.
A Quantization-Friendly Separable Convolution for MobileNets
TLDR
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.
High Resolution Photography with an RGB-Infrared Camera
TLDR
A novel image formation model for RGB-IR cameras that can be easily calibrated, and an efficient algorithm that jointly addresses three restoration problems - channel deblurring, channel separation and pixel demosaicing - using quadratic image regularizers are proposed.
...
1
2
3
...