Search Results for author: Maria Vanrell

Found 7 papers, 1 papers with code

Intrinsic Decomposition of Document Images In-the-Wild

1 code implementation29 Nov 2020 Sagnik Das, Hassan Ahmed Sial, Ke Ma, Ramon Baldrich, Maria Vanrell, Dimitris Samaras

However, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and textures and; (b) synthetic or hybrid datasets with non-realistic, simulated lighting conditions are used to train the models.

Document Shadow Removal Intrinsic Image Decomposition +1

Light Direction and Color Estimation from Single Image with Deep Regression

no code implementations18 Sep 2020 Hassan A. Sial, Ramon Baldrich, Maria Vanrell, Dimitris Samaras

We present a method to estimate the direction and color of the scene light source from a single image.


Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects

no code implementations14 Sep 2020 Hassan Sial, Ramon Baldrich, Maria Vanrell

Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues.

Understanding trained CNNs by indexing neuron selectivity

no code implementations1 Feb 2017 Ivet Rafegas, Maria Vanrell, Luis A. Alexandre, Guillem Arias

The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized.

Understanding learned CNN features through Filter Decoding with Substitution

no code implementations16 Nov 2015 Ivet Rafegas, Maria Vanrell

This provides us with a new tool to directly visualize any CNN single neuron as a filter in the first layer, this is in terms of the image space.

The Photometry of Intrinsic Images

no code implementations CVPR 2014 Marc Serra, Olivier Penacchio, Robert Benavente, Maria Vanrell, Dimitris Samaras

The proposed mathematical formulation includes information about the color of the illuminant and the effects of the camera sensors, both of which modify the observed color of the reflectance of the objects in the scene during the acquisition process.

3D Reconstruction Color Constancy +2

Cannot find the paper you are looking for? You can Submit a new open access paper.