Related papers: Scan2LoD3: Reconstructing semantic 3D building mod…

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…

Vision-language models (VLMs) have shown promise in 2D medical image analysis, but extending them to 3D remains challenging due to the high computational demands of volumetric data and the difficulty of aligning 3D spatial features with…

Loop closing is a fundamental part of simultaneous localization and mapping (SLAM) for autonomous mobile systems. In the field of visual SLAM, bag of words (BoW) has achieved great success in loop closure. The BoW features for loop…

Dense semantic 3D reconstruction is typically formulated as a discrete or continuous problem over label assignments in a voxel grid, combining semantic and depth likelihoods in a Markov Random Field framework. The depth and semantic…

We propose PyTorchGeoNodes, a differentiable module for reconstructing 3D objects and their parameters from images using interpretable shape programs. Unlike traditional CAD model retrieval, shape programs allow reasoning about semantic…

In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…

Abstract representations of 3D scenes play a crucial role in computer vision, enabling a wide range of applications such as mapping, localization, surface reconstruction, and even advanced tasks like SLAM and rendering. Among these…

Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image. So far, most of the previous methods still struggle to extract semantic…

3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitively understandable to humans. Existing approaches for 3D…

Current medical vision-language models (VLMs) process volumetric brain MRI using 2D slice-based approximations, fragmenting the spatial context required for accurate neuroradiological interpretation. We developed \textbf{Brain3D}, a staged…

We introduce multi-slice reasoning, a new notion for single-view 3D reconstruction which challenges the current and prevailing belief that multi-view synthesis is the most natural conduit between single-view and 3D. Our key observation is…

3D reconstruction from a single view image is a long-standing prob-lem in computer vision. Various methods based on different shape representations(such as point cloud or volumetric representations) have been proposed. However,the 3D shape…

Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevertheless, traditional techniques such as global feature…

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…

Advancements in 3D instance segmentation have traditionally been tethered to the availability of annotated datasets, limiting their application to a narrow spectrum of object categories. Recent efforts have sought to harness vision-language…

Semantic segmentation of large-scale outdoor point clouds is essential for urban scene understanding in various applications, especially autonomous driving and urban high-definition (HD) mapping. With rapid developments of mobile laser…

In this paper we present our workflow to automatically reconstruct 3D building models based on 2D building polygons and a LiDAR point cloud. The workflow generates models at different levels of detail (LoDs) to support data requirements of…

3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature…

Grounding natural language in 3D environments is a critical step toward achieving robust 3D vision-language alignment. Current datasets and models for 3D visual grounding predominantly focus on identifying and localizing objects from…

The integration of molecular and natural language representations has emerged as a focal point in molecular science, with recent advancements in Language Models (LMs) demonstrating significant potential for comprehensive modeling of both…