Related papers: BuildingBRep-11K: Precise Multi-Storey B-Rep Build…
Capsule networks (CapsNets) are superior at modeling hierarchical spatial relationships but suffer from two critical limitations: high computational cost due to iterative dynamic routing and poor robustness under input corruptions. To…
Advances in deep learning techniques have allowed recent work to reconstruct the shape of a single object given only one RBG image as input. Building on common encoder-decoder architectures for this task, we propose three extensions: (1)…
Accurate classification of buildings into residential and non-residential categories is crucial for urban planning, infrastructure development, population estimation and resource allocation. It is a complex job to carry out automatic…
Determining material properties from camera images can expand the ability to identify complex objects in indoor environments, which is valuable for consumer robotics applications. To support this, we introduce MatPredict, a dataset that…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but continue to struggle with geometric reasoning, primarily due to the perception bottleneck regarding fine-grained visual elements. While formal languages have…
A dataset of 35,608 materials with their topological properties is constructed by combining the density functional theory (DFT) results of Materiae and the Topological Materials Database. Thanks to this, machine-learning approaches are…
There has been increasing interest in smart factories powered by robotics systems to tackle repetitive, laborious tasks. One impactful yet challenging task in robotics-powered smart factory applications is robotic grasping: using robotic…
We introduce Version 3 (V3) of the gridded near real-time Multi-Source Weighted-Ensemble Precipitation (MSWEP) product -- the first fully global, historical machine learning powered precipitation (P) dataset, developed to meet the growing…
A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and…
The growing demand for detailed building roof data has driven the development of automated extraction methods to overcome the inefficiencies of traditional approaches, particularly in handling complex variations in building geometries.…
Boundary representation (B-rep) is the de facto standard for modern CAD, yet learning-based B-rep synthesis remains challenging due to the tight coupling between discrete topology and continuous geometry. We observe a fundamental asymmetry…
The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis.…
Neural architecture search (NAS) has become a common approach to developing and discovering new neural architectures for different target platforms and purposes. However, scanning the search space is comprised of long training processes of…
Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense…
Multilayer bootstrap network builds a gradually narrowed multilayer nonlinear network from bottom up for unsupervised nonlinear dimensionality reduction. Each layer of the network is a nonparametric density estimator. It consists of a group…
Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly derived from either…
Recent approaches for predicting layouts from 360 panoramas produce excellent results. These approaches build on a common framework consisting of three steps: a pre-processing step based on edge-based alignment, prediction of layout…
Recognizing geometric features on B-rep models is a cornerstone technique for multimedia content-based retrieval and has been widely applied in intelligent manufacturing. However, previous research often merely focused on Machining Feature…
This paper introduces a new real and synthetic dataset called NeRFBK specifically designed for testing and comparing NeRF-based 3D reconstruction algorithms. High-quality 3D reconstruction has significant potential in various fields, and…
Recently, there has been growing interest in developing learning-based methods to detect and utilize salient semi-global or global structures, such as junctions, lines, planes, cuboids, smooth surfaces, and all types of symmetries, for 3D…