Results 21 to 26 of about 21,019 (26)
A factorization approach to inertial affine structure from motion [PDF]
, 2016 We consider the problem of reconstructing a 3-D scene from a moving camera with high frame rate using the affine projection model. This problem is traditionally known as Affine Structure from Motion (Affine SfM), and can be solved using an elegant low ...
Tron, Roberto
core
CLD-shaped Brushstrokes in Non-Photorealistic Rendering
, 2010 Rendering techniques based on a random grid can be improved by adapting brushstrokes to the shape of different areas of the original picture. In this paper, the concept of Coherence Length Diagram is applied to determine the adaptive brushstrokes, in ...
Marazzato, Roberto +1 more
core
Dipole and Quadrupole Moments in Image Processing [PDF]
, 2009 This paper proposes an algorithm for image processing, obtained by adapting to image maps the definitions of two well-known physical quantities. These quantities are the dipole and quadrupole moments of a charge distribution.
Sparavigna, Amelia
core +1 more source
Unsupervised feature learning by augmenting single images [PDF]
, 2014 When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm.
Brox, Thomas +2 more
core
Color Dipole Moments for Edge Detection
, 2009 Dipole and higher moments are physical quantities used to describe a charge distribution. In analogy with electromagnetism, it is possible to define the dipole moments for a gray-scale image, according to the single aspect of a gray-tone map.
Sparavigna, Amelia
core
NeurAll: Towards a Unified Visual Perception Model for Automated Driving
Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc.
Chennupati, Sumanth +6 more
core