mlsanityData to 7 Oct 2026

VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distribution

arXiv 2502.17880 ↗First posted 25 Feb 2025cs.CR cs.CV cs.MMcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality, color recovery, and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 32 of its 56 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

32 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct

Other references · 31

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2022Diffusion Models in Vision: A Surveycited by 1,008
  7. 2021Score-based Generative Modeling in Latent Spacecited by 634
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  10. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  11. 2020Information Leakage in Embedding Modelscited by 199
  12. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
19 more
  1. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  2. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  3. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  4. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  5. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  6. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  7. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  8. 2020Multiscale Point Cloud Geometry Compressioncited by 72
  9. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 69
  10. 2019Learned Point Cloud Geometry Compressioncited by 58
  11. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  12. 2022Shape-invariant 3D Adversarial Point Cloudscited by 49
  13. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  14. 2021Denoising Diffusion Gamma Modelscited by 27
  15. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  16. 2021Multiscale deep context modeling for lossless point cloud geometry compressioncited by 21
  17. 2021LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networkscited by 19
  18. 2022Learning-based Lossless Point Cloud Geometry Coding using Sparse Tensorscited by 8
  19. 2020Security and Privacy for Mobile Edge Caching: Challenges and Solutionscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models
  2. 2024DiffPoint: Single and Multi-view Point Cloud Reconstruction with ViT Based Diffusion Model
  3. 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
  4. 2025Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images
  5. 2025Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
  6. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Clouds
  7. 2025DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
  8. 2024Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction