paper-with-me

Papers

Curvature-Regularized Variational Autoencoder for 3D Scene Reconstruction from Sparse Depth

2025-12-05 · Maryam Yousefi, Soodeh Bakhshandeh arxiv

When depth sensors provide only 5% of needed measurements, reconstructing complete 3D scenes becomes difficult. Autonomous vehicles and robots cannot tolerate the geometric errors that sparse reconstruction introduces. We propose curvature regularization through a discrete Laplacian operator, achieving 18.1% better reconstruction accuracy than standard variational autoencoders. Our contribution challenges an implicit assumption in geometric deep learning: that combining multiple geometric constraints improves performance. A single well-designed regularization term not only matches but exceeds the effectiveness of complex multi-term formulations. The discrete Laplacian offers stable gradients and noise suppression with just 15% training overhead and zero inference cost. Code and models are available at https://github.com/Maryousefi/GeoVAE-3D.

📄 PDF Abstract BibTeX arXiv:2512.05783

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehicles

Similar Papers 제목 키워드 기반

Attribute Regularized Soft Introspective Variational Autoencoder for Interpretable Cardiac Disease Classification

2023-12-14 · Maxime Di Folco, Cosmin I. Bercea, Julia A. Schnabel

Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. In this paper, we propose a novel interpretable approach that combines attribute regular…

Attribute

Interpretable Representation Learning of Cardiac MRI via Attribute Regularization

2024-06-12 · Maxime Di Folco, Cosmin I. Bercea, Emily Chan, Julia A. Schnabel

Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. Several approaches have been recently considered to encode attributes in the latent spac…

AttributeRepresentation Learning

$Γ$-VAE: Curvature regularized variational autoencoders for uncovering emergent low dimensional geometric structure in high dimensional data

2024-03-02 · Jason Z. Kim, Nicolas Perrin-Gilbert, Erkan Narmanli, Paul Klein 외

Natural systems with emergent behaviors often organize along low-dimensional subsets of high-dimensional spaces. For example, despite the tens of thousands of genes in the human genome, the principled study of genomics i…

Dimensionality Reduction

Mixed-curvature Variational Autoencoders

2019-11-19 · ICLR 2020 1 · Ondrej Skopek, Octavian-Eugen Ganea, Gary Bécigneul

Euclidean geometry has historically been the typical "workhorse" for machine learning applications due to its power and simplicity. However, it has recently been shown that geometric spaces with constant non-zero curvatu…

Curvature Regularized Surface Reconstruction from Point Cloud

2020-01-22 · Yuchen He, Sung Ha Kang, Hao Liu

We propose a variational functional and fast algorithms to reconstruct implicit surface from point cloud data with a curvature constraint. The minimizing functional balances the distance function from the point cloud and…

Computational EfficiencySurface Reconstruction