Related papers: Deep Learning-based Scalable Image-to-3D Facade Pa…

3D LiDAR point cloud data is crucial for scene perception in computer vision, robotics, and autonomous driving. Geometric and semantic scene understanding, involving 3D point clouds, is essential for advancing autonomous driving…

This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to…

Three-dimensional (3D) urban models have gained interest because of their applications in many use-cases such as urban planning and virtual reality. However, generating these 3D representations requires LiDAR data, which are not always…

Encouraged by the growing availability of pre-trained 2D diffusion models, image-to-3D generation by leveraging Score Distillation Sampling (SDS) is making remarkable progress. Most existing methods combine novel-view lifting from 2D…

We introduce Generalizable 3D-Language Feature Fields (g3D-LF), a 3D representation model pre-trained on large-scale 3D-language dataset for embodied tasks. Our g3D-LF processes posed RGB-D images from agents to encode feature fields for:…

Differentiable rendering aims to compute the derivative of the image rendering function with respect to the rendering parameters. This paper presents a novel algorithm for 6-DoF pose estimation through gradient-based optimization using a…

We propose PartField, a feedforward approach for learning part-based 3D features, which captures the general concept of parts and their hierarchy without relying on predefined templates or text-based names, and can be applied to open-world…

Standard registration algorithms need to be independently applied to each surface to register, following careful pre-processing and hand-tuning. Recently, learning-based approaches have emerged that reduce the registration of new scans to…

Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models…

Feature detectors and descriptors are key low-level vision tools that many higher-level tasks build on. Unfortunately these fail in the presence of challenging light transport effects including partial occlusion, low contrast, and…

We introduce LUCIE-3D, a lightweight three-dimensional climate emulator designed to capture the vertical structure of the atmosphere, respond to climate change forcings, and maintain computational efficiency with long-term stability.…

We present a novel pipeline for learning the conditional distribution of a building roof mesh given pixels from an aerial image, under the assumption that roof geometry follows a set of regular patterns. Unlike alternative methods that…

The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and…

The past decade has seen the advent of numerous building energy efficiency visualization and simulation systems; however, most of them rely on theoretical thermal models to suggest building structural design for new constructions and…

Facial expressions recognition (FER) of 3D face scans has received a significant amount of attention in recent years. Most of the facial expression recognition methods have been proposed using mainly 2D images. These methods suffer from…

3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due to deficiencies in supervisory signals, such as sparse or…

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and…

Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that augments visual…

We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are subsequently fed to a…

To address the issues of weak correlation between multi-view features, low recognition accuracy of small-scale targets, and insufficient robustness in complex scenarios in underground pipeline detection using 3D GPR, this paper proposes a…