Search Results for author:
Found 7 papers, 0 papers with code
Low Compute and Fully Parallel Computer Vision With HashMatch
Numerous computer vision problems such as stereo depth estimation, object-class segmentation and foreground/background segmentation can be formulated as per-pixel image labeling tasks.
UltraStereo: Efficient Learning-Based Matching for Active Stereo Systems
Efficient estimation of depth from pairs of stereo images is one of the core problems in computer vision.
The Global Patch Collider
In contrast to conventional approaches that rely on pairwise distance computation, our algorithm isolates distinctive pixel pairs that hit the same leaf during traversal through multiple learned tree structures.
HyperDepth: Learning Depth From Structured Light Without Matching
We contribute an algorithm for solving this correspondence problem efficiently, without compromising depth accuracy.
Filter Forests for Learning Data-Dependent Convolutional Kernels
We propose 'filter forests' (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context.
Ask the Image: Supervised Pooling to Preserve Feature Locality
In this paper we propose a weighted supervised pooling method for visual recognition systems.
iCub World: Friendly Robots Help Building Good Vision Data-Sets
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform.
