Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

Published: 16 Jan 2024, Last Modified: 11 Feb 2024ICLR 2024 posterEveryoneRevisionsBibTeX
Supplementary Material: zip
Primary Area: generative models
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: Neural Radiance Fields, 3D generation, generative 3D models
Submission Guidelines: I certify that this submission complies with the submission instructions as described on
TL;DR: We introduce Magic123, a novel coarse-to-fine pipeline for high-quality image-to-3D generation that uses a joint 2D and 3D prior to guide the novel views
Abstract: We present ``Magic123'', a two-stage coarse-to-fine approach for high-quality, textured 3D mesh generation from a single image in the wild using both 2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference-view supervision and novel-view guidance by a joint 2D and 3D diffusion prior. We introduce a trade-off parameter between the 2D and 3D priors to control the details and 3D consistencies of the generation. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on diverse synthetic and real-world images.
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.
Submission Number: 5136