Skip to main content
EXTENDED SEARCH
Log in
Top
Published in:
Read chapter Read first chapter

2025 | OriginalPaper | Chapter

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image Using Latent Video Diffusion

Authors : Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani

Published in: Computer Vision – ECCV 2024

Publisher: Springer Nature Switzerland

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

SV3D introduces a groundbreaking method for generating consistent novel views and high-quality 3D meshes from a single image by leveraging a video diffusion model. This model, adapted from Stable Video Diffusion (SVD), demonstrates excellent multi-view consistency and generalization capabilities, surpassing previous methods that rely on image-based diffusion models. By repurposing the temporal consistency of video diffusion models for spatial 3D object consistency, SV3D achieves controllable and high-resolution multi-view synthesis. The chapter also presents a comprehensive pipeline for 3D generation, including techniques like coarse-to-fine training, disentangled illumination modeling, and masked score distillation sampling (SDS) loss, which significantly enhance the quality of the generated 3D meshes. Extensive experiments and comparisons with state-of-the-art methods demonstrate the superior performance of SV3D in both novel view synthesis and 3D generation, making it a significant contribution to the field of computer vision and AI.
AI Generated

This summary of the content was generated with the help of AI.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

inform now
previous chapter ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
next chapter WordRobe: Text-Guided Generation of Textured 3D Garments
Appendix
This content is only visible if you are logged in and have the appropriate permissions.
Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image Using Latent Video Diffusion
Authors
Vikram Voleti
Chun-Han Yao
Mark Boss
Adam Letts
David Pankratz
Dmitry Tochilkin
Christian Laforte
Robin Rombach
Varun Jampani
Copyright Year
2025
Book
Computer Vision – ECCV 2024

Print ISBN: 978-3-031-73231-7

Electronic ISBN: 978-3-031-73232-4

Copyright Year: 2025

DOI
https://doi.org/10.1007/978-3-031-73232-4_25

Premium Partner

    Image Credits