activity
20172023
most citedDeep Bilateral Learning for Real-Time Image Enhancement

832 citations · 838 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2023

MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction

Yuwen Heng, Yihong Wu, Jiawen Chen +2

Achieving accurate material segmentation for 3-channel RGB images is challenging due to the considerable variation in a material's appearance. Hyperspectral images, which are sets…

cs.CV20211 cited

Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image

Shumian Xin, Neal Wadhwa, Tianfan Xue +5

We present a method that takes as input a single dual-pixel image, and simultaneously estimates the image's defocus map -- the amount of defocus blur at each pixel -- and recovers…

cs.CV2020

Real-time Localized Photorealistic Video Style Transfer

Xide Xia, Tianfan Xue, Wei-sheng Lai +4

We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photore…

cs.CV20205 cited

Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer

Xide Xia, Meng Zhang, Tianfan Xue +4

Photorealistic style transfer is the task of transferring the artistic style of an image onto a content target, producing a result that is plausibly taken with a camera. Recent app…

cs.CV2019

Stereoscopic Dark Flash for Low-light Photography

Jian Wang, Tianfan Xue, Jonathan T. Barron +1

In this work, we present a camera configuration for acquiring "stereoscopic dark flash" images: a simultaneous stereo pair in which one camera is a conventional RGB sensor, but the…

cs.CV2018

Wireless Software Synchronization of Multiple Distributed Cameras

Sameer Ansari, Neal Wadhwa, Rahul Garg +1

We present a method for precisely time-synchronizing the capture of image sequences from a collection of smartphone cameras connected over WiFi. Our method is entirely software-bas…