Miao Zhang   

Associate Professor
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates

MORE> Recommended Ph.D.Supervisor Recommended MA Supervisor Institutional Repository Personal Page
Language:English

Paper Publications

Title of Paper:Unrolled Optimization with Deep Priors for Intrinsic Image Decomposition

Hits:

Date of Publication:2018-01-01

Key Words:intrinsic image decomposition; deep networks; implicit priors; unrolled optimization

Abstract:Intrinsic image decomposition is a challenging task, which aims at separating an image into reflectance and shading layers. Traditionally, strong hand-crafted priors such as reflectance sparsity, shading smoothness and depth information, have been used to solve this long-standing ill-posed problem including two variables. Recent researches lay emphasis on the deep neural networks which need to be specific design. To overcome these limitations, we develop a novel unrolled optimization model for intrinsic image decomposition, which incorporate deep priors from the optimization perspective in a more skillful way, rather than directly design the specific network or introduce hand-crafted and human annotation priors. Extensive experimental results illustrate the excellent performance of our method compared with other state-of-the-art methods and we successfully carry out the proposed algorithm for the application based on image decomposition (e.g. low-light image enhancement).

Address: No.2 Linggong Road, Ganjingzi District, Dalian City, Liaoning Province, P.R.C., 116024
Click:    MOBILE Version DALIAN UNIVERSITY OF TECHNOLOGY Login

Open time:..

The Last Update Time: ..