Related papers: ZippyPoint: Fast Interest Point Detection, Descrip…

Deep convolutional networks have recently achieved great success in video recognition, yet their practical realization remains a challenge due to the large amount of computational resources required to achieve robust recognition. Motivated…

Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We…

The advent of a panoply of resource limited devices opens up new challenges in the design of computer vision algorithms with a clear compromise between accuracy and computational requirements. In this paper we present new binary image…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing…

Efficient matching of local image features is a fundamental task in many computer vision applications. However, the real-time performance of top matching algorithms is compromised in computationally limited devices, such as mobile phones or…

Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments. In…

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to…

We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with…

Interest point detection is a common task in various computer vision applications. Although a big variety of detector are developed so far computational efficiency of interest point based image analysis remains to be the problem. Current…

The task of detecting the interest points in 3D meshes has typically been handled by geometric methods. These methods, while greatly describing human preference, can be ill-equipped for handling the variety and subjectivity in human…

Feature descriptor matching is a critical step is many computer vision applications such as image stitching, image retrieval and visual localization. However, it is often affected by many practical factors which will degrade its…

Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditional methods, such…

Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to…

Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport…

Fast binary descriptors build the core for many vision based applications with real-time demands like object detection, Visual Odometry or SLAM. Commonly it is assumed, that the acquired images and thus the patches extracted around…

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of…

Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an…

We present tidychangepoint, a new R package for changepoint detection analysis. Most R packages for segmenting univariate time series focus on providing one or two algorithms for changepoint detection that work with a small set of models…

This work addresses the challenge of sub-pixel accuracy in detecting 2D local features, a cornerstone problem in computer vision. Despite the advancements brought by neural network-based methods like SuperPoint and ALIKED, these modern…