Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

by   Steve Dias Da Cruz, et al.

Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously trained machine learning models. Image normalization is hence a valuable preprocessing component to enhance the models' robustness. To this end, we introduce a new strategy for the cost function formulation of encoder-decoder networks to average out all the unimportant information in the input images (e.g. environmental features and illumination changes) to focus on the reconstruction of the salient features (e.g. class instances). Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety. Its applicability is assessed on three publicly available datasets. We combine the triplet loss as a regularizer in the latent space representation and a nearest neighbour search to improve the generalization to unseen illuminations and class instances. The importance of the aforementioned post-processing is highlighted on an automotive application. To this end, we release a synthetic dataset of sceneries from three different passenger compartments where each scenery is rendered under ten different illumination and environmental conditions: see


page 1

page 3

page 4

page 5

page 7

page 8


Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme

The image relighting task of transferring illumination conditions betwee...

Image Dehazing via Joint Estimation of Transmittance Map and Environmental Illumination

Haze limits the visibility of outdoor images, due to the existence of fo...

ALCN: Adaptive Local Contrast Normalization

To make Robotics and Augmented Reality applications robust to illuminati...

Illumination-Based Color Reconstruction for the Dynamic Vision Sensor

This work demonstrates a novel, state of the art method to reconstruct c...

WDRN : A Wavelet Decomposed RelightNet for Image Relighting

The task of recalibrating the illumination settings in an image to a tar...

A Multi-Domain Feature Learning Method for Visual Place Recognition

Visual Place Recognition (VPR) is an important component in both compute...

How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change

Direct visual localization has recently enjoyed a resurgence in populari...

Please sign up or login with your details

Forgot password? Click here to reset