• Publications
  • Influence
Perceptual Evaluation of Color‐to‐Grayscale Image Conversions
TLDR
This paper presents the results of two subjective experiments in which a total of 24 color images were converted to grayscale using seven state‐of‐the‐art conversions and evaluated by 119 human subjects using a paired comparison paradigm to be the first perceptual evaluation of color‐to‐grayscale conversions. Expand
Evaluation of HDR tone mapping methods using essential perceptual attributes
TLDR
This work presents an overview about the effects of basic image attributes in high dynamic range tone mapping, and proposes a scheme of relationships between these attributes, leading to the definition of an overall image quality measure. Expand
FFT and Convolution Performance in Image Filtering on GPU
TLDR
Conditions under which the FFT gives better performance than the corresponding convolution are identified and the different kernel sizes and issues of application of multiple filters on one image are assessed. Expand
Automatic photo-to-terrain alignment for the annotation of mountain pictures
TLDR
A novel automatic technique is proposed to avoid the burden of manual registration of a given photograph with a 3D geo-referenced terrain model, able to automatically derive the pose of the camera relative to the geometric terrain model. Expand
An Efficient Perception-based Adaptive Color to Gray Transformation
TLDR
A new color to grayscale transformation is presented, based on the experimental background of the Coloroid system observations, and a new simple, yet very efficient method is introduced to solve the inconsistency of the field. Expand
New measurements reveal weaknesses of image quality metrics in evaluating graphics artifacts
TLDR
This work runs two experiments where observers use a brush-painting interface to directly mark image regions with noticeable/objectionable distortions in the presence/absence of a high-quality reference image, respectively, and shows a relatively high correlation between the with-reference and no-reference observer markings. Expand
Absolute pose estimation from line correspondences using direct linear transformation
TLDR
This work proposes a novel method 'DLT-Combined-Lines' based on the Direct Linear Transformation (DLT) algorithm, which benefits from a new combination of two existing DLT methods for pose estimation, and is the most accurate method on real world data, outperforming the state-of-the-art by a large margin. Expand
Ink-and-ray: Bas-relief meshes for adding global illumination effects to hand-drawn characters
TLDR
A new approach for generating global illumination renderings of hand-drawn characters using only a small set of simple annotations that exploits the concept of bas-relief sculptures, and forms an optimization process that automatically constructs approximate geometry sufficient to evoke the impression of a consistent 3D shape. Expand
Learning to Predict Localized Distortions in Rendered Images
TLDR
A new data-driven full-reference image quality metric is proposed which outperforms current state-of-the-art metrics and is trained on subjective ground truth data combining two publicly available datasets. Expand
Camera Pose Estimation from Lines using Plücker Coordinates
TLDR
This work proposes a novel algebraic algorithm to estimate the camera pose using Pl\"ucker coordinates that allow linear projection of the lines into the image and an algebraic approach to handle mismatched line correspondences. Expand
...
1
2
3
4
5
...