mlsanityData to 14 Oct 2026

VoluMe -- Authentic 3D Video Calls from Live Gaussian Splat Prediction

arXiv 2507.21311 ↗First posted 28 Jul 2025cs.CV cs.GRcited by 3

Not on the map. Why?

Abstract (arXiv)

Virtual 3D meetings offer the potential to enhance copresence, increase engagement and thus improve effectiveness of remote meetings compared to standard 2D video calls. However, representing people in 3D meetings remains a challenge; existing solutions achieve high quality by using complex hardware, making use of fixed appearance via enrolment, or by inverting a pre-trained generative model. These approaches lead to constraints that are unwelcome and ill-fitting for videoconferencing applications. We present the first method to predict 3D Gaussian reconstructions in real time from a single 2D webcam feed, where the 3D representation is not only live and realistic, but also authentic to the input video. By conditioning the 3D representation on each video frame independently, our reconstruction faithfully recreates the input video from the captured viewpoint (a property we call authenticity), while generalizing realistically to novel viewpoints. Additionally, we introduce a stability loss to obtain reconstructions that are temporally stable on video sequences. We show that our method delivers state-of-the-art accuracy in visual quality and stability metrics compared to existing methods, and demonstrate our approach in live one-to-one 3D meetings using only a standard 2D camera and display. This demonstrates that our approach can allow anyone to communicate volumetrically, via a method for 3D videoconferencing that is not only highly accessible, but also realistic and authentic.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

33 of 45 references.

References · 33

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  7. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  8. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  9. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  10. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  11. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
21 more
  1. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
  2. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  3. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  4. 2022Instant Volumetric Head Avatarscited by 159
  5. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  6. 2023Relightable Gaussian Codec Avatarscited by 127
  7. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  8. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  9. 2023FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embeddingcited by 108
  10. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  11. 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
  12. 2022Learning Neural Parametric Head Modelscited by 73
  13. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  14. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 53
  15. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 53
  16. 2023TriPlaneNet: An Encoder for EG3D Inversioncited by 41
  17. 2022VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representationscited by 36
  18. 2024Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Capturescited by 34
  19. 2024Look Ma, no markers: holistic performance capture without the hasslecited by 23
  20. 2024FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Headscited by 22
  21. 2022Technological Factors Influencing Videoconferencing and Zoom Fatiguecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025ExGS: Extreme 3D Gaussian Compression with Diffusion Priorscited by 1
  2. 2026ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptationcited by 1
  3. 2026Photorealistic Novel View Synthesis of Human Faces using Next-Scale Transformerscited by 0