Related papers: Orientation-boosted Voxel Nets for 3D Object Recog…

Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not…

Deep Convolutional Neural Networks (CNNs) have been repeatedly proven to perform well on image classification tasks. Object detection methods, however, are still in need of significant improvements. In this paper, we propose a new framework…

We propose a novel method for instance label segmentation of dense 3D voxel grids. We target volumetric scene representations, which have been acquired with depth sensors or multi-view stereo methods and which have been processed with…

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature…

Recent advances in deep learning have led to significant progress in the computer vision field, especially for visual object recognition tasks. The features useful for object classification are learned by feed-forward deep convolutional…

While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem, but…

Convolutional neural nets (CNN) are the leading computer vision method for classifying images. In some cases, it is desirable to classify only a specific region of the image that corresponds to a certain object. Hence, assuming that the…

Oriented object detection is a fundamental yet challenging task in remote sensing (RS), aiming to locate and classify objects with arbitrary orientations. Recent advancements in deep learning have significantly enhanced the capabilities of…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing…

We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more generally. Both tasks take as input the raw image and a binary mask…

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification…

Many machine learning problems involve regressing variables on a non-Euclidean manifold -- e.g. a discrete probability distribution, or the 6D pose of an object. One way to tackle these problems through gradient-based learning is to use a…

In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular,…

The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…

Visual localization determines an agent's precise position and orientation within an environment using visual data. It has become a critical task in the field of robotics, particularly in applications such as autonomous navigation. This is…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

We present a novel approach for oriented object detection, named TricubeNet, which localizes oriented objects using visual cues ($i.e.,$ heatmap) instead of oriented box offsets regression. We represent each object as a 2D Tricube kernel…

We consider the task of estimating the 3D orientation of an object of known category given an image of the object and a bounding box around it. Recently, CNN-based regression and classification methods have shown significant performance…

We present a novel approach to the detection and 3D pose estimation of objects in color images. Its main contribution is that it does not require any training phases nor data for new objects, while state-of-the-art methods typically require…