Abstract Design of hardware accelerators for neural network (NN) applications involves
walking a tight rope amidst the constraints of low-power, high accuracy and throughput …

Stereo matching is one of the longest-standing problems in computer vision with close to 40
years of studies and research. Throughout the years the paradigm has shifted from local …

We introduce LightGlue, a deep neural network that learns to match local features across
images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse …

Abstract 3D object detection is an essential task in autonomous driving. Recent techniques
excel with highly accurate detection rates, provided the 3D input data is obtained from …

Detecting objects such as cars and pedestrians in 3D plays an indispensable role in
autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for …

We propose a cost volume-based neural network for depth inference from multi-view
images. We demonstrate that building a cost volume pyramid in a coarse-to-fine manner …

Estimating depth from RGB images is a long-standing ill-posed problem, which has been
explored for decades by the computer vision, graphics, and machine learning communities …

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to
regress dense disparity maps from stereo pairs. These models, however, suffer from a …

This paper reports on the NTIRE 2024 challenge on HR Depth From images of Specular and
Transparent surfaces held in conjunction with the New Trends in Image Restoration and …

Tessaratoma papillosa (Drury) first invaded Taiwan in 2009. Every year, T. papillosa causes
severe damage to the longan crops. Novel applications for edge intelligence are applied in …