Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression

12/08/2015
by   Takuya Narihira, et al.
0

We introduce a new approach to intrinsic image decomposition, the task of decomposing a single image into albedo and shading components. Our strategy, which we term direct intrinsics, is to learn a convolutional neural network (CNN) that directly predicts output albedo and shading channels from an input RGB image patch. Direct intrinsics is a departure from classical techniques for intrinsic image decomposition, which typically rely on physically-motivated priors and graph-based inference algorithms. The large-scale synthetic ground-truth of the MPI Sintel dataset plays a key role in training direct intrinsics. We demonstrate results on both the synthetic images of Sintel and the real images of the classic MIT intrinsic image dataset. On Sintel, direct intrinsics, using only RGB input, outperforms all prior work, including methods that rely on RGB+Depth input. Direct intrinsics also generalizes across modalities; it produces quite reasonable decompositions on the real images of the MIT dataset. Our results indicate that the marriage of CNNs with synthetic training data may be a powerful new technique for tackling classic problems in computer vision.

READ FULL TEXT

page 2

page 6

page 8

research
08/26/2018

CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering

Intrinsic image decomposition is a challenging, long-standing computer v...
research
07/30/2018

Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition

Intrinsic image decomposition is the process of separating the reflectan...
research
12/23/2016

DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition

We present a new deep supervised learning method for intrinsic decomposi...
research
11/20/2020

Intrinsic Image Decomposition using Paradigms

Intrinsic image decomposition is the classical task of mapping image to ...
research
10/25/2022

Search for Concepts: Discovering Visual Concepts Using Direct Optimization

Finding an unsupervised decomposition of an image into individual object...
research
05/02/2017

Shading Annotations in the Wild

Understanding shading effects in images is critical for a variety of vis...
research
06/13/2019

IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination

Intrinsic image decomposition describes an image based on its reflectanc...

Please sign up or login with your details

Forgot password? Click here to reset