Related papers: Image-Based Place Recognition on Bucolic Environme…

Autonomous navigation in unstructured off-road environments is greatly improved by semantic scene understanding. Conventional image processing algorithms are difficult to implement and lack robustness due to a lack of structure and high…

We present a novel approach for relocalization or place recognition, a fundamental problem to be solved in many robotics, automation, and AR applications. Rather than relying on often unstable appearance information, we consider a situation…

We present a new point-based approach for modeling the appearance of real scenes. The approach uses a raw point cloud as the geometric representation of a scene, and augments each point with a learnable neural descriptor that encodes local…

Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a…

Visual localization and mapping is the key technology underlying the majority of mixed reality and robotics systems. Most state-of-the-art approaches rely on local features to establish correspondences between images. In this paper, we…

Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be…

Recognizing dynamic scenes is one of the fundamental problems in scene understanding, which categorizes moving scenes such as a forest fire, landslide, or avalanche. While existing methods focus on reliable capturing of static and dynamic…

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…

Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. their visual similarity. However, visual similarity does not…

Visual localization is the problem of estimating the position and orientation from which a given image (or a sequence of images) is taken in a known scene. It is an important part of a wide range of computer vision and robotics…

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban…

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…

In this paper, we investigate a new framework for image classification that adaptively generates spatial representations. Our strategy is based on a sequential process that learns to explore the different regions of any image in order to…

Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision…

Change detection is an important problem in vision field, especially for aerial images. However, most works focus on traditional change detection, i.e., where changes happen, without considering the change type information, i.e., what…

Recent advancements in statistical learning and computational abilities have enabled autonomous vehicle technology to develop at a much faster rate. While many of the architectures previously introduced are capable of operating under highly…

We propose an image representation and matching approach that substantially improves visual-based location estimation for images. The main novelty of the approach, called distinctive visual element matching (DVEM), is its use of…

Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex…

Vision based localization is the problem of inferring the pose of the camera given a single image. One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with…

Hierarchical visual localization methods achieve state-of-the-art accuracy but require substantial memory as they need to store all database images. Direct 2D-3D matching requires significantly less memory but suffers from lower accuracy…