Discriminative feature encoding for intrinsic image decomposition  

作　　者：Zongji Wang Yunfei Liu Feng Lu 

机构地区：[1]Key Laboratory of Network Information System Technology(NIST),Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100190,China [2]State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering,Beihang University,Beijing 100191,China [3]Peng Cheng Laboratory,Shenzhen 518000,China

出　　处：《Computational Visual Media》2023年第3期597-618,共22页计算可视媒体（英文版）

基　　金：supported by the Special Funds for Creative Research(Grant No.2022C61540);the National Natural Science Foundation of China(NSFC,Grant Nos.61972012 and 61732016).

摘　　要：Intrinsic image decomposition is an important and long-standing computer vision problem.Given an input image,recovering the physical scene properties is ill-posed.Several physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image decomposition.This work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high efficiency.The focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input image.To achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding space.We define feature distribution divergence to efficiently separate the feature vectors of different intrinsic components.The feature distributions are also constrained to fit the real ones through a feature distribution consistency.In addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image decomposition.Our method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent frames.Experimental results indicate that our proposed network structure can outperform the existing state-of-the-art.

关 键 词：intrinsic image decomposition deep learning feature distribution data refinement 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]