Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 857

The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.

Magic3D: High-Resolution Text-to-3D Content Creation

Open access
Lin, Chen-Hsuan, Gao, Jun, Tang, Luming, Takikawa, Towaki, Zeng, Xiaohui, Huang, Xun, Kreis, Karsten, Fidler, Sanja, Liu, Ming-Yu, Lin, Tsung-Yi·2023·2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

DreamFusion [31] has recently demonstrated the utility of a pretrained text-to-image diffusion model to optimize Neural Radiance Fields (NeRF) [23], achieving remarkable text-to-3D synthesis results. However, the method has two inherent limitations: (a) extremely slow optimization of NeRF and (b) low-resolution image space supervision on NeRF, leading to low-quality 3D models with a long processing time. In this paper, we address these limitations by utilizing a two-stage optimization framework. First, we obtain a coarse model using a low-resolution diffusion prior and accelerate with a sparse 3D hash grid structure. Using the coarse representation as the initialization, we further optimize a textured 3D mesh model with an efficient differentiable renderer interacting with a high-resolution latent diffusion model. Our method, dubbed Magic3D, can create high quality 3D mesh models in 40 minutes, which is 2× faster than DreamFusion (reportedly taking 1.5 hours on average), while also achieving higher resolution. User studies show 61.7% raters to prefer our approach over DreamFusion. Together with the image-conditioned generation capabilities, we provide users with new ways to control 3D synthesis, opening up new avenues to various creative applications.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52729.2023.00037

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 44 references

Research works printed but not linked: 8

  1. ibing, 2021, Octree transformer: Autoregressive 3d shape generation on hierarchically structured sequences, ArXiv Preprint
  2. liu, 2020, Neural sparse voxel fields, Advances in neural information processing systems, 33, 15651
  3. 10.1145/3414685.3417861 · doi:10.1145/3414685.3417861
  4. zhang, 2021, Image gans meet differentiable rendering for inverse graphics and interpretable 3d neural rendering, International Conference on Learning Representations
  5. takikawa, 2022, Kaolin wisp A pytorch library and engine for neural fields research
  6. smith, 2017, Improved adversarial systems for 3d object generation and reconstruction, Conference on Robot Learning, 87
  7. achlioptas, 2018, Learning representations and generative models for 3d point clouds, International Conference on Machine Learning, 40
  8. schwarz, 0, Voxgraf: Fast 3d-aware image synthesis with sparse voxel grids, Advances in Neural IInformation Processing Systems

Cited by

See all 857

Metadata

Authors
Lin, C.-H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.-Y., & Lin, T.-Y.
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
300-309
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4386065887
Cited by
857
References
44
FWCI
187.60
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Magic3D: High-Resolution Text-to-3D Content Creation. https://app.cochat.ai/papers/10.1109/cvpr52729.2023.00037
The paper
Lin, C.-H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.-Y., & Lin, T.-Y. (2023). Magic3D: High-Resolution Text-to-3D Content Creation. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr52729.2023.00037

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.