JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling

Jingyang Zhang, Shiwei Li, Yuanxun Lu, Tian Fang, David Neil McKinnon, Yanghai Tsin, Long Quan, Yao Yao

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Generative AI, Computer Vision, Machine Learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce JointNet that finetunes existing RGB diffusion models for modeling the joint distribution of images and an additional dense modality (e.g., depth, normal).

Abstract:

We introduce JointNet, a novel neural network architecture for modeling the joint distribution of images and an additional dense modality (e.g., depth maps).
JointNet is extended from a pre-trained text-to-image diffusion model, where a copy of the original network is created for the new dense modality branch and is densely connected with the RGB branch.
The RGB branch is locked during network fine-tuning, which enables efficient learning of the new modality distribution while maintaining the strong generalization ability of the large-scale pre-trained diffusion model.
We demonstrate the effectiveness of JointNet by using the RGB-D diffusion as an example and through extensive experiments, showcasing its applicability in a variety of applications, including joint RGB-D generation, dense depth prediction, depth-conditioned image generation, and high-resolution 3D panorama generation.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: generative models

Submission Number: 3497