English
Related papers

Related papers: Unified Primitive Proxies for Structured Shape Com…

200 papers

In this paper a new system for piecewise primitive surface recovery on point clouds is presented, which allows a novice user to sketch areas of interest in order to guide the fitting process. The algorithm is demonstrated against a…

Graphics · Computer Science 2017-01-23 Daniel Beale

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Yaqi Zhao , Wang Lin , Zijian Zhang , Miles Yang , Jingyuan Chen , Wentao Zhang , Zhao Zhong , Liefeng Bo

We describe a method to parse a complex, cluttered indoor scene into primitives which offer a parsimonious abstraction of scene structure. Our primitives are simple convexes. Our method uses a learned regression procedure to parse a scene…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Vaibhav Vavilala , David Forsyth

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Mingyue Yang , Yuxin Wen , Weikai Chen , Yongwei Chen , Kui Jia

Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of real grasps on…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Matthias Humt , Dominik Winkelbauer , Ulrich Hillenbrand

3D shape reconstruction from a single image is a highly ill-posed problem. Modern deep learning based systems try to solve this problem by learning an end-to-end mapping from image to shape via a deep network. In this paper, we aim to solve…

Computer Vision and Pattern Recognition · Computer Science 2019-08-02 Kejie Li , Ravi Garg , Ming Cai , Ian Reid

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Benoit Guillard , Edoardo Remelli , Pascal Fua

The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects. Recent methods learn to represent an object shape using a set of simple primitives to fit the target.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Di Liu , Long Zhao , Qilong Zhangli , Yunhe Gao , Ting Liu , Dimitris N. Metaxas

Searching for a unified scene representation remains a research challenge in computer graphics. Traditional mesh-based representations are unsuitable for dense, fuzzy elements, and introduce additional complexity for filtering and…

Graphics · Computer Science 2024-09-24 Yang Zhou , Songyin Wu , Ling-Qi Yan

We present UniPlane, a novel method that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations and associate them across the video for the final…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Yuzhong Huang , Chen Liu , Ji Hou , Ke Huo , Shiyu Dong , Fred Morstatter

Semantic-aware 3D reconstruction from sparse, unposed images remains challenging for feed-forward 3D Gaussian Splatting (3DGS). Existing methods often predict an over-complete set of Gaussian primitives under sparse-view supervision,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Guibiao Liao , Qian Ren , Kaimin Liao , Hua Wang , Zhi Chen , Luchao Wang , Yaohua Tang

3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Salman H. Khan , Yulan Guo , Munawar Hayat , Nick Barnes

Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However, existing methods select only informative and relevant views using…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Youngju Na , Woo Jae Kim , Kyu Beom Han , Suhyeon Ha , Sung-eui Yoon

We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point…

Computer Vision and Pattern Recognition · Computer Science 2022-06-24 Gopal Sharma , Bidya Dash , Aruni RoyChowdhury , Matheus Gadelha , Marios Loizou , Liangliang Cao , Rui Wang , Erik Learned-Miller , Subhransu Maji , Evangelos Kalogerakis

We present a dynamic reconstruction system that receives a casual monocular RGB video as input, and outputs a complete and persistent reconstruction of the scene. In other words, we reconstruct not only the the currently visible parts of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Kirill Mazur , Marwan Taher , Andrew J. Davison

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Chiyu Max Jiang , Avneesh Sud , Ameesh Makadia , Jingwei Huang , Matthias Nießner , Thomas Funkhouser

We propose a feed-forward Gaussian Splatting model that unifies 3D scene and semantic field reconstruction. Combining 3D scenes with semantic fields facilitates the perception and understanding of the surrounding environment. However, key…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Qijian Tian , Xin Tan , Jingyu Gong , Yuan Xie , Lizhuang Ma

Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Junhwa Hur , Charles Herrmann , Songyou Peng , Philipp Henzler , Zeyu Ma , Todd Zickler , Deqing Sun

The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D models, and no existing pre-training method is equally…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Ziyi Wang , Yanran Zhang , Jie Zhou , Jiwen Lu

Autonomous UAV path planning for 3D reconstruction has been actively studied in various applications for high-quality 3D models. However, most existing works have adopted explore-then-exploit, prior-based or exploration-based strategies,…

Robotics · Computer Science 2024-01-19 Chen Feng , Haojia Li , Fei Gao , Boyu Zhou , Shaojie Shen