Release Time:2020-02-12  Hits:

Indexed by: Conference Paper

Date of Publication: 2019-01-01

Included Journals: CPCI-S、EI

Volume: 2019-July

Page Number: 1462-1467

Key Words: Intrinsic image decomposition; physical imaging principle; residual dense block; deep learning

Abstract: Intrinsic image decomposition is a challenging task, which aims at recovering intrinsic components from the observation. Hand-crafted priors have been widely used in traditional methods, yet with unsatisfactory performance of quality and runtime. Recently, network-based approaches have been greatly developed, but the physical imaging principle is ignored causing the product of estimated components is hard to reconstruct the observation. To overcome these limitations, we develop an enhanced residual dense intrinsic network (ERDIN) for intrinsic decomposition. Specifically, we construct the basic module (i.e., enhanced residual dense block (ERDB)) to fully exploit the hierarchical features. The physical imaging principle is designed as the reconstruction loss to ensure the consistency between the observation and the product of estimated components, which is of equal importance with the data loss. Extensive experimental results illustrate our excellent performance compared with other state-of-the-art methods.