Alert button
Picture for Ben Poole

Ben Poole

Alert button

Disentangled 3D Scene Generation with Layout Learning

Feb 26, 2024
Dave Epstein, Ben Poole, Ben Mildenhall, Alexei A. Efros, Aleksander Holynski

Viaarxiv icon

Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion

Dec 06, 2023
Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton

Viaarxiv icon

ReconFusion: 3D Reconstruction with Diffusion Priors

Dec 05, 2023
Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P. Srinivasan, Dor Verbin, Jonathan T. Barron, Ben Poole, Aleksander Holynski

Viaarxiv icon

Variational Prediction

Jul 14, 2023
Alexander A. Alemi, Ben Poole

Figure 1 for Variational Prediction
Figure 2 for Variational Prediction
Figure 3 for Variational Prediction
Viaarxiv icon

Diffusion Self-Guidance for Controllable Image Generation

Jun 11, 2023
Dave Epstein, Allan Jabri, Ben Poole, Alexei A. Efros, Aleksander Holynski

Figure 1 for Diffusion Self-Guidance for Controllable Image Generation
Figure 2 for Diffusion Self-Guidance for Controllable Image Generation
Figure 3 for Diffusion Self-Guidance for Controllable Image Generation
Figure 4 for Diffusion Self-Guidance for Controllable Image Generation
Viaarxiv icon

Learning a Diffusion Prior for NeRFs

Apr 27, 2023
Guandao Yang, Abhijit Kundu, Leonidas J. Guibas, Jonathan T. Barron, Ben Poole

Figure 1 for Learning a Diffusion Prior for NeRFs
Figure 2 for Learning a Diffusion Prior for NeRFs
Figure 3 for Learning a Diffusion Prior for NeRFs
Viaarxiv icon

DreamBooth3D: Subject-Driven Text-to-3D Generation

Mar 27, 2023
Amit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer, Nataniel Ruiz, Ben Mildenhall, Shiran Zada, Kfir Aberman, Michael Rubinstein, Jonathan Barron, Yuanzhen Li, Varun Jampani

Figure 1 for DreamBooth3D: Subject-Driven Text-to-3D Generation
Figure 2 for DreamBooth3D: Subject-Driven Text-to-3D Generation
Figure 3 for DreamBooth3D: Subject-Driven Text-to-3D Generation
Figure 4 for DreamBooth3D: Subject-Driven Text-to-3D Generation
Viaarxiv icon

VeLO: Training Versatile Learned Optimizers by Scaling Up

Nov 17, 2022
Luke Metz, James Harrison, C. Daniel Freeman, Amil Merchant, Lucas Beyer, James Bradbury, Naman Agrawal, Ben Poole, Igor Mordatch, Adam Roberts, Jascha Sohl-Dickstein

Figure 1 for VeLO: Training Versatile Learned Optimizers by Scaling Up
Figure 2 for VeLO: Training Versatile Learned Optimizers by Scaling Up
Figure 3 for VeLO: Training Versatile Learned Optimizers by Scaling Up
Figure 4 for VeLO: Training Versatile Learned Optimizers by Scaling Up
Viaarxiv icon

Imagen Video: High Definition Video Generation with Diffusion Models

Oct 05, 2022
Jonathan Ho, William Chan, Chitwan Saharia, Jay Whang, Ruiqi Gao, Alexey Gritsenko, Diederik P. Kingma, Ben Poole, Mohammad Norouzi, David J. Fleet, Tim Salimans

Figure 1 for Imagen Video: High Definition Video Generation with Diffusion Models
Figure 2 for Imagen Video: High Definition Video Generation with Diffusion Models
Figure 3 for Imagen Video: High Definition Video Generation with Diffusion Models
Figure 4 for Imagen Video: High Definition Video Generation with Diffusion Models
Viaarxiv icon

DreamFusion: Text-to-3D using 2D Diffusion

Sep 29, 2022
Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall

Figure 1 for DreamFusion: Text-to-3D using 2D Diffusion
Figure 2 for DreamFusion: Text-to-3D using 2D Diffusion
Figure 3 for DreamFusion: Text-to-3D using 2D Diffusion
Figure 4 for DreamFusion: Text-to-3D using 2D Diffusion
Viaarxiv icon