Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Diffusion

Diffusion

Diffusion is the passive movement of substances down their concentration gradients—requiring no expenditure of cellular energy. Substances, such as molecules or ions, diffuse from an area of high concentration to an area of low concentration in the cytosol or across membranes. Eventually, the concentration will even out, with the substance moving randomly but causing no net change in concentration. Such a state is called dynamic equilibrium, which is essential for maintaining overall...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A framework of digital biomarkers for neurodegenerative diseases.

Nature reviews bioengineering·2026

Same author

SocialGen: Modeling Multi-Human Social Interaction with Language Models.

Proceedings. International Conference on 3D Vision·2026

Same author

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026

Same author

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026

Same authorSame journal

LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2026

Same author

Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation.

Advances in neural information processing systems·2026

Same journal

Multi-Modal Deep Clustering Survival Machines for Alzheimer's Disease Subtype Discovery.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2026

Same journal

Self-Supervised Anomaly Detection from Anomalous Training Data via Iterative Latent Token Masking.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2024

Same journal

Robust AMD Stage Grading with Exclusively OCTA Modality Leveraging 3D Volume.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2024

Same journal

STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2024

Same journal

Learning to Learn: How to Continuously Teach Humans and Machines.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision·2024

See all related articles

Search research articles

Home
Repurposing 2d Diffusion Models With Gaussian Atlas For 3d Generation.

Home
Repurposing 2d Diffusion Models With Gaussian Atlas For 3d Generation.

Related Experiment Video

Planar Gradient Diffusion System to Investigate Chemotaxis in a 3D Collagen Matrix

Planar Gradient Diffusion System to Investigate Chemotaxis in a 3D Collagen Matrix

Published on: June 12, 2015

Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation.

Tiange Xiang^1,2, Kai Li², Chengjiang Long²

¹Stanford University.

... IEEE International Conference on Computer Vision Workshops. IEEE International Conference on Computer Vision

|April 6, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

Researchers repurposed 2D diffusion models for 3D object generation using Gaussian Atlas. This novel approach leverages a large dataset, GaussianVerse, to create 3D Gaussians from 2D models, advancing 3D content creation.

More Related Videos

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Published on: August 11, 2016

Diffusion Imaging in the Rat Cervical Spinal Cord

Diffusion Imaging in the Rat Cervical Spinal Cord

Published on: April 7, 2015

Related Experiment Videos

Planar Gradient Diffusion System to Investigate Chemotaxis in a 3D Collagen Matrix

Planar Gradient Diffusion System to Investigate Chemotaxis in a 3D Collagen Matrix

Published on: June 12, 2015

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography

Published on: August 11, 2016

Diffusion Imaging in the Rat Cervical Spinal Cord

Diffusion Imaging in the Rat Cervical Spinal Cord

Published on: April 7, 2015

Area of Science:

Computer Vision
Machine Learning
3D Graphics

Background:

Advances in 2D text-to-image diffusion models are rapid due to abundant 2D data.
3D diffusion model development lags due to limited high-quality 3D data, impacting performance.
Existing 3D generative models face challenges with data scarcity and computational complexity.

Purpose of the Study:

To address the scarcity of 3D data for diffusion models.
To adapt powerful pre-trained 2D diffusion models for 3D object generation.
To develop a novel representation and dataset for efficient 3D diffusion model training.

Main Methods:

Introduced Gaussian Atlas, a novel representation using dense 2D grids for 3D Gaussian generation.
Fine-tuned pre-trained 2D diffusion models on a 2D manifold derived from 3D structures.

Compiled GaussianVerse, a large-scale dataset of 205K 3D Gaussian fittings for model training.

Main Results:

Demonstrated successful transfer learning from 2D to 3D diffusion models.
Generated high-quality 3D Gaussians using adapted text-to-image models.
Showcased the effectiveness of Gaussian Atlas and GaussianVerse for 3D content generation.

Conclusions:

Pre-trained 2D diffusion models can be effectively repurposed for 3D object generation.
The proposed method bridges the performance gap between 2D and 3D diffusion models.
Gaussian Atlas and GaussianVerse offer a viable solution for large-scale 3D generative modeling.