mlsanityData to 14 Oct 2026

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

arXiv 2512.05783 ↗First posted 5 Dec 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

29 of 46 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  9. 2017Mixed Precision Trainingcited by 1,156
  10. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 710
17 more
  1. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  2. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  3. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  4. 2021Score-based Generative Modeling in Latent Spacecited by 636
  5. 2015Generating Sentences from a Continuous Spacecited by 612
  6. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  7. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  10. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  11. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  12. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  13. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 93
  14. 2019Preventing Posterior Collapse with delta-VAEscited by 86
  15. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 86
  16. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  17. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50

Built on by

Not cited yet.