Related papers: Geometry Meets Vision: Revisiting Pretrained Seman…
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…
Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), such as CLIP, for dense prediction. However, VLMs, pre-trained…
Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted…
We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Lack of annotated data prohibits direct inference of 3D semantic priors; instead, current…
Understanding the 3D semantics of a scene is a fundamental problem for various scenarios such as embodied agents. While NeRFs and 3DGS excel at novel-view synthesis, previous methods for understanding their semantics have been limited to…
Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation…
Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately,…
Visual localization remains challenging in dynamic environments where fluctuating lighting, adverse weather, and moving objects disrupt appearance cues. Despite advances in feature representation, current absolute pose regression methods…
3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits…
A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world. One of the key issues is to describe the visual relationships between objects. When dealing with real world data,…
Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…
Although cluttered indoor scenes have a lot of useful high-level semantic information which can be used for mapping and localization, most Visual Odometry (VO) algorithms rely on the usage of geometric features such as points, lines and…
While 3D reconstruction is a well-established and widely explored research topic, semantic 3D reconstruction has only recently witnessed an increasing share of attention from the Computer Vision community. Semantic annotations allow in fact…
Nowadays the accurate geo-localization of ground-view images has an important role across domains as diverse as journalism, forensics analysis, transports, and Earth Observation. This work addresses the problem of matching a query…
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The…
Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in…
Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…
Recent advances in feature learning have shown that self-supervised vision foundation models can capture semantic correspondences but often lack awareness of underlying 3D geometry. GECO addresses this gap by producing geometrically…
Image stitching often faces challenges due to varying capture angles, positional differences, and object movements, leading to misalignments and visual discrepancies. Traditional seam carving methods neglect semantic information, causing…
Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the…