Structured Outdoor Architecture Reconstruction by Exploration and
Classification
- URL: http://arxiv.org/abs/2108.07990v1
- Date: Wed, 18 Aug 2021 06:28:26 GMT
- Title: Structured Outdoor Architecture Reconstruction by Exploration and
Classification
- Authors: Fuyang Zhang, Xiang Xu, Nelson Nauata, Yasutaka Furukawa
- Abstract summary: We present an explore-and-classify framework for structured architectural reconstruction from an aerial image.
We learn to classify the correctness of building models while generating classification labels based on the ground-truth.
We evaluate the approach using initial reconstructions by two baselines and two state-of-the-art reconstruction algorithms.
- Score: 34.066110654930476
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents an explore-and-classify framework for structured
architectural reconstruction from an aerial image. Starting from a potentially
imperfect building reconstruction by an existing algorithm, our approach 1)
explores the space of building models by modifying the reconstruction via
heuristic actions; 2) learns to classify the correctness of building models
while generating classification labels based on the ground-truth, and 3)
repeat. At test time, we iterate exploration and classification, seeking for a
result with the best classification score. We evaluate the approach using
initial reconstructions by two baselines and two state-of-the-art
reconstruction algorithms. Qualitative and quantitative evaluations demonstrate
that our approach consistently improves the reconstruction quality from every
initial reconstruction.
Related papers
- ReMatching Dynamic Reconstruction Flow [55.272357926111454]
We introduce the ReMatching framework, designed to improve generalization quality by incorporating deformation priors into dynamic reconstruction models.
The framework is highly adaptable and can be applied to various dynamic representations.
Our evaluations on popular benchmarks involving both synthetic and real-world dynamic scenes demonstrate a clear improvement in reconstruction accuracy of current state-of-the-art models.
arXiv Detail & Related papers (2024-11-01T16:09:33Z) - StructRe: Rewriting for Structured Shape Modeling [63.792684115318906]
We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling.
Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures.
arXiv Detail & Related papers (2023-11-29T10:35:00Z) - Hierarchical clustering with dot products recovers hidden tree structure [53.68551192799585]
In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure.
We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance.
We demonstrate that the tree output by this algorithm provides a bona fide estimate of generative hierarchical structure in data, under a generic probabilistic graphical model.
arXiv Detail & Related papers (2023-05-24T11:05:12Z) - ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation [28.445041795260906]
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders.
We show that by modeling such comprehensive structures more complete and regularized reconstructions can be achieved.
arXiv Detail & Related papers (2022-05-29T05:30:33Z) - Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D
Reconstruction [47.38670633513938]
We learn a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories.
Our work relies on segmented image collections for learning 3D of generic categories.
arXiv Detail & Related papers (2022-04-07T17:59:25Z) - Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases [131.50372468579067]
We represent the reconstructed surface as an atlas, using a neural network.
We empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.
arXiv Detail & Related papers (2021-04-14T16:21:22Z) - Generative Tomography Reconstruction [11.460692362624533]
We propose an end-to-end differentiable architecture for tomography reconstruction that maps a noisy sinogram into a denoised reconstruction.
We also propose a generative model that, given a noisy sinogram, can sample realistic reconstructions.
arXiv Detail & Related papers (2020-10-26T18:22:37Z) - Curved Buildings Reconstruction from Airborne LiDAR Data by Matching and
Deforming Geometric Primitives [13.777047260469677]
We propose a new framework for curved building reconstruction via assembling and deforming geometric primitives.
The presented framework is validated on several highly curved buildings collected by various LiDAR in different cities.
arXiv Detail & Related papers (2020-03-22T16:05:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.