Related papers: MVL-Loc: Leveraging Vision-Language Model for Gene…

We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse,…

Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized…

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for…

Visual localization is the task of accurate camera pose estimation in a known scene. It is a key problem in computer vision and robotics, with applications including self-driving cars, Structure-from-Motion, SLAM, and Mixed Reality.…

3D layout tasks have traditionally concentrated on geometric constraints, but many practical applications demand richer contextual understanding that spans social interactions, cultural traditions, and usage conventions. Existing methods…

While multimodal large language models (MLLMs) have demonstrated extraordinary vision-language understanding capabilities, their abilities to solve instance-level visual-language problems beyond a single image warrant further exploration.…

Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the…

For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance. Map-aided localization is a universal approach to overcome the limitations of global navigation satellite system…

We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected…

We consider the problem of relative pose regression in visual relocalization. Recently, several promising approaches have emerged in this area. We claim that even though they demonstrate on the same datasets using the same split to train…

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal…

Visual localization is one of the most important components for robotics and autonomous driving. Recently, inspiring results have been shown with CNN-based methods which provide a direct formulation to end-to-end regress 6-DoF absolute…

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint,…

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…

Rather than having each newly deployed robot create its own map of its surroundings, the growing availability of SLAM-enabled devices provides the option of simply localizing in a map of another robot or device. In cases such as multi-robot…

Cross-view geo-localisation identifies coarse geographical position of an automated vehicle by matching a ground-level image to a geo-tagged satellite image from a database. Despite the advancements in Cross-view geo-localisation,…

Existing deep learning based visual servoing approaches regress the relative camera pose between a pair of images. Therefore, they require a huge amount of training data and sometimes fine-tuning for adaptation to a novel scene.…

Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by…

Vision-and-Language Navigation (VLN) requires grounding instructions, such as "turn right and stop at the door", to routes in a visual environment. The actual grounding can connect language to the environment through multiple modalities,…