English
Related papers

Related papers: BrickAnything: Geometry-Conditioned Buildable Bric…

200 papers

Additive robotic construction of building-scale discrete bar structures, such as trusses and space frames, is increasingly attractive due to the potential improvements in efficiency, safety, and design possibilities. However, programming…

Robotics · Computer Science 2021-11-10 Yijiang Huang , Caelan Garrett , Ian Ting , Stefana Parascho , Caitlin Mueller

In this paper, we propose a novel network framework for indoor 3D object detection to handle variable input frame numbers in practical scenarios. Existing methods only consider fixed frames of input data for a single detector, such as…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Zhenyu Wu , Xiuwei Xu , Ziwei Wang , Chong Xia , Linqing Zhao , Jiwen Lu , Haibin Yan

Generating articulated assets is crucial for robotics, digital twins, and embodied intelligence. Existing generative models often rely on single-view inputs representing closed states, resulting in ambiguous or unrealistic kinematic…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Haowen Wang , Xiaoping Yuan , Fugang Zhang , Rui Jian , Yuanwei Zhu , Xiuquan Qiao , Yakun Huang

Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD). However, automatically generating valid and high-quality B-rep models remains challenging due to the complex interdependence between…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Jing Li , Yihang Fu , Falai Chen

Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capability, termed compositional 3D reconstruction, is pivotal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Mingyu Dong , Chong Xia , Mingyuan Jia , Weichen Lyu , Long Xu , Zheng Zhu , Yueqi Duan

We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Xin Kang , Zihan Zheng , Lei Chu , Yue Gao , Jiahao Li , Hao Pan , Xuejin Chen , Yan Lu

The reconstruction of 3D microstructures from 2D slices is considered to hold significant value in predicting the spatial structure and physical properties of materials.The dimensional extension from 2D to 3D is viewed as a highly…

Machine Learning · Computer Science 2024-02-27 Yilin Zheng , Zhigong Song

We introduce ProcGen3D, a new approach for 3D content creation by generating procedural graph abstractions of 3D objects, which can then be decoded into rich, complex 3D assets. Inspired by the prevalent use of procedural generators in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xinyi Zhang , Daoyi Gao , Naiqi Li , Angela Dai

We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Xueqi Ma , Yilin Liu , Wenjun Zhou , Ruowei Wang , Hui Huang

The entertainment industry relies on 3D visual content to create immersive experiences, but traditional methods for creating textured 3D models can be time-consuming and subjective. Generative networks such as StyleGAN have advanced image…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Yi-Ting Pan , Chai-Rong Lee , Shu-Ho Fan , Jheng-Wei Su , Jia-Bin Huang , Yung-Yu Chuang , Hung-Kuo Chu

We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…

Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models. However, existing approaches lack a general and unified way of representing structural and semantic conditioning at…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Luca Butera , Andrea Cini , Alberto Ferrante , Cesare Alippi

We present TreeON, a novel neural-based framework for reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and its corresponding Digital Surface Model (DSM). Our method introduces a new…

Graphics · Computer Science 2026-03-12 Angeliki Grammatikaki , Johannes Eschner , Pedro Hermosilla , Oscar Argudo , Manuela Waldner

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yiwen Tang , Ray Zhang , Jiaming Liu , Zoey Guo , Dong Wang , Zhigang Wang , Bin Zhao , Shanghang Zhang , Peng Gao , Hongsheng Li , Xuelong Li

In this work, we present a robotic solution to automate the task of wall construction. To that end, we present an end-to-end visual perception framework that can quickly detect and localize bricks in a clutter. Further, we present a light…

Robotics · Computer Science 2021-07-28 Mohit Vohra , Ashish Kumar , Ravi Prakash , Laxmidhar Behera

We propose a novel method to generate fabrication blueprints from images of carpentered items. While 3D reconstruction from images is a well-studied problem, typical approaches produce representations that are ill-suited for computer-aided…

Computer Vision and Pattern Recognition · Computer Science 2021-07-22 James Noeckel , Haisen Zhao , Brian Curless , Adriana Schulz

Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D…

Graphics · Computer Science 2026-05-21 Xin Zhang , Yabo Chen , Yijie Fang , Wanying Qu , Haibin Huang , Chi Zhang , Feng Xu , Xuelong Li

Modern experimental methods enable the creation of self-assembly building blocks with tunable interactions, but optimally exploiting this tunability for the self-assembly of desired structures remains an important challenge. Many studies of…

Soft Condensed Matter · Physics 2025-07-10 Maximilian C. Hübl , Carl P. Goodrich

We are given a set of elements in a metric space. The distribution of the elements is arbitrary, possibly adversarial. Can we weigh the elements in a way that is resistant to such (adversarial) manipulations? This problem arises in various…

Machine Learning · Computer Science 2026-02-18 Damien Berriaud , Roger Wattenhofer

Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text. Previous works face problems with single-category generation, low-frequency 3D details, and requiring a large number of paired datasets for training. To…

Computer Vision and Pattern Recognition · Computer Science 2023-11-15 Bo Han , Yitong Fu , Yixuan Shen