Semantic Hierarchical Priors for Intrinsic Image Decomposition

02/11/2019
by   Saurabh Saini, et al.
14

Intrinsic Image Decomposition (IID) is a challenging and interesting computer vision problem with various applications in several fields. We present novel semantic priors and an integrated approach for single image IID that involves analyzing image at three hierarchical context levels. Local context priors capture scene properties at each pixel within a small neighbourhood. Mid-level context priors encode object level semantics. Global context priors establish correspondences at the scene level. Our semantic priors are designed on both fixed and flexible regions, using selective search method and Convolutional Neural Network features. Our IID method is an iterative multistage optimization scheme and consists of two complementary formulations: L_2 smoothing for shading and L_1 sparsity for reflectance. Experiments and analysis of our method indicate the utility of our semantic priors and structured hierarchical analysis in an IID framework. We compare our method with other contemporary IID solutions and show results with lesser artifacts. Finally, we highlight that proper choice and encoding of prior knowledge can produce competitive results even when compared to end-to-end deep learning IID methods, signifying the importance of such priors. We believe that the insights and techniques presented in this paper would be useful in the future IID research.

READ FULL TEXT

page 3

page 7

page 9

page 11

page 12

page 13

page 14

page 15

research
09/25/2022

Discriminative feature encoding for intrinsic image decomposition

Intrinsic image decomposition is an important and long-standing computer...
research
11/22/2019

Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

Intrinsic image decomposition, which is an essential task in computer vi...
research
06/14/2021

Context-Aware Image Inpainting with Learned Semantic Priors

Recent advances in image inpainting have shown impressive results for ge...
research
04/16/2018

Semantic Single-Image Dehazing

Single-image haze-removal is challenging due to limited information cont...
research
10/01/2021

Generative Memory-Guided Semantic Reasoning Model for Image Inpainting

Most existing methods for image inpainting focus on learning the intra-i...
research
12/21/2020

Image Annotation based on Deep Hierarchical Context Networks

Context modeling is one of the most fertile subfields of visual recognit...
research
07/18/2020

Deep Hough-Transform Line Priors

Classical work on line segment detection is knowledge-based; it uses car...

Please sign up or login with your details

Forgot password? Click here to reset