The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
Open accessAbstract
A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field. This setup aggregates 2D scores at multiple camera viewpoints into a 3D score, and re-purposes a pretrained 2D model for 3D data generation. We identify a technical challenge of distribution mismatch that arises in this application, and propose a novel estimation mechanism to resolve it. We run our algorithm on several off-the-shelf diffusion image generative models, including the recently released Stable Diffusion trained on the large-scale LAION 5B dataset.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712 · cited 6×
“01 , 157] [13] in the case of DDPM. Score as mean-shift.”
BackgroundMethodInfluentialNeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852
3D ShapeNets: A deep representation for volumetric shapes
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298801 · Cited by 4,550
Mean shift, mode seeking, and clustering
Cheng, Y. (1995) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.400568 · Cited by 3,856
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 3×
“A diffusion model could be interpreted as either a VAE [13, 49] or a denoising score-matcher [50, 52, 56].”
BackgroundPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528 · cited 1×
“In terms of implementation, we do not have access to the close-sourced Imagen [46] diffusion model.”
BackgroundHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
ShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953 · cited 5×
“…as DDPM [13] parameterized the ConvNet to instead predict a noise residual ˆ ϵ , and these models can be converted back to the form of a denoiser by [52] In this paper, we treat all pretrained diffusion models as denoisers, and perform the interface conversion in our implementation when needed.”
BackgroundMethodInfluentialGenerative Modeling by Estimating Gradients of the Data Distribution
Song, Y., & Ermon, S. (2019) · arXiv · doi:10.48550/arxiv.1907.05600 · Cited by 1,453
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
Wu, J., Zhang, C., Xue, T., Freeman, W. T., & Tenenbaum, J. B. (2016) · arXiv · doi:10.48550/arxiv.1610.07584 · Cited by 1,393 · cited 1×
“Many prior works [2, 58, 60] perform 3D generative modeling by training on 3D datasets [5, 24, 54, 59].”
BackgroundPlenoxels: Radiance Fields without Neural Networks
Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., & Kanazawa, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00542 · Cited by 1,388
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Martin-Brualla, R., Radwan, N., Sajjadi, M. S. M., Barron, J. T., Dosovitskiy, A., & Duckworth, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00713 · Cited by 1,374
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03365 · Cited by 1,245
TensoRF: Tensorial Radiance Fields
Chen, A., Xu, Z., Geiger, A., Yu, J., & Su, H. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19824-3_20 · Cited by 1,184
Classifier-Free Diffusion Guidance
Ho, J., & Salimans, T. (2022) · arXiv · doi:10.48550/arxiv.2207.12598 · Cited by 1,126 · cited 1×
“The model is natively trained for text-conditioned image generations, and exposes a guidance scale parameter that controls the strength of language conditioning [14].”
BackgroundEfficient Geometry-aware 3D Generative Adversarial Networks
Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., de Mello, S., Gallo, O., Guibas, L., Tremblay, J., Khamis, S., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01565 · Cited by 1,093
Optical models for direct volume rendering
Max, N. (1995) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/2945.468400 · Cited by 1,059
LAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
A Connection Between Score Matching and Denoising Autoencoders
Vincent, P. (2011) · Neural Computation · doi:10.1162/neco_a_00142 · Cited by 1,011
Mean shift analysis and applications
Comaniciu, D., & Meer, P. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790416 · Cited by 987
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
Sun, C., Sun, M., & Chen, H.-T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00538 · Cited by 939
(2005) · doi:10.5555/1046920.1088696 · Cited by 756
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
Niemeyer, M., & Geiger, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01129 · Cited by 731
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
Chan, E. R., Monteiro, M., Kellnhofer, P., Wu, J., & Wetzstein, G. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00574 · Cited by 689
PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows
Yang, G., Huang, X., Hao, Z., Liu, M.-Y., Belongie, S., & Hariharan, B. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00464 · Cited by 656 · cited 1×
“Many prior works [2, 58, 60] perform 3D generative modeling by training on 3D datasets [5, 23, 55, 59].”
BackgroundUNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
Oechsle, M., Peng, S., & Geiger, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00554 · Cited by 622
Mitsuba 2: a retargetable forward and inverse renderer
Nimier-David, M., Vicini, D., Zeltner, T., & Jakob, W. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356498 · Cited by 550
Elucidating the Design Space of Diffusion-Based Generative Models
Karras, T., Aittala, M., Aila, T., & Laine, S. (2022) · neural information processing systems · doi:10.52202/068431-1926 · Cited by 538
ABC: A Big CAD Model Dataset for Geometric Deep Learning
Koch, S., Matveev, A., Jiang, Z., Williams, F., Artemov, A., Burnaev, E., Alexa, M., Zorin, D., & Panozzo, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00983 · Cited by 534
Improved Techniques for Training Score-Based Generative Models
Song, Y., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2006.09011 · Cited by 482
DreamFusion: Text-to-3D using 2D Diffusion
Poole, B., Jain, A., Barron, J. T., & Mildenhall, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.14988 · Cited by 474
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Sun, X., Wu, J., Zhang, X., Zhang, Z., Zhang, C., Xue, T., Tenenbaum, J. B., & Freeman, W. T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00314 · Cited by 455
OpenDR: An Approximate Differentiable Renderer
Loper, M. M., & Black, M. J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_11 · Cited by 441
Differentiable Monte Carlo ray tracing through edge sampling
Li, T.-M., Aittala, M., Durand, F., & Lehtinen, J. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275109 · Cited by 428
Zero-Shot Text-Guided Object Generation with Dream Fields
Jain, A., Mildenhall, B., Barron, J. T., Abbeel, P., & Poole, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00094 · Cited by 388
Kingma, D. P., Salimans, T., Poole, B., & Ho, J. (2021) · arXiv · doi:10.48550/arxiv.2107.00630 · Cited by 374
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., & Yang, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00768 · Cited by 340
Diffusion Models as Plug-And-Play Priors
Graikos, A., Malkin, N., Jojić, N., & Samaras, D. (2022) · neural information processing systems · doi:10.52202/068431-1070 · Cited by 332
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
Schwarz, K., Liao, Y., Niemeyer, M., & Geiger, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02442 · Cited by 314
Text2Mesh: Text-Driven Neural Stylization for Meshes
Michel, O., Bar-On, R., Liu, R., Benaim, S., & Hanocka, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01313 · Cited by 289
Pulsar: Efficient Sphere-based Neural Rendering
Lassner, C., & Zollhöfer, M. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00149 · Cited by 267
Learning Gradient Fields for Shape Generation
Cai, R., Yang, G., Averbuch-Elor, H., Hao, Z., Belongie, S., Snavely, N., & Hariharan, B. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58580-8_22 · Cited by 225
AvatarCLIP: zero-shot text-driven generation and animation of 3D avatars
Hong, F., Zhang, M., Pan, L., Cai, Z., Yang, L., & Liu, Z. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530094 · Cited by 217
CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
Mohammad Khalid, N., Xie, T., Belilovsky, E., & Popa, T. (2022) · SIGGRAPH Asia 2022 Conference Papers · doi:10.1145/3550469.3555392 · Cited by 190
FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space OptimizationPreprint
Liu, X., Gong, C., Wu, L., Zhang, S., Su, H., & Liu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.01573 · Cited by 95
ReLU Fields: The Little Non-linearity That Could
Karnewar, A., Ritschel, T., Wang, O., & Mitra, N. J. (2022) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3528233.3530707 · Cited by 93
Zhu, S. C., Yuille, A., & Mumford, D. B. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026531017760 · Cited by 86
CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
Niemeyer, M., & Geiger, A. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00103 · Cited by 72
Understanding Pure CLIP Guidance for Voxel Grid NeRF ModelsPreprint
Lee, H.-H., & Chang, A. X. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.15172 · Cited by 52
ClipMatrix: Text-controlled Creation of 3D Textured MeshesPreprint
Jetchev, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12922 · Cited by 50
Pix2Scene: Learning Implicit 3D Representations from Images
Rajeswar, S., Mannan, F., Golemo, F., Vázquez, D., Nowrouzezahrai, D., & Courville, A. C. (2018) · Cited by 5
Cited by
Zero-1-to-3: Zero-shot One Image to 3D Object
Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00853 · Cited by 841
Wonder3D: Single Image to 3D Using Cross-Domain Diffusion
Long, X., Guo, Y.-C., Lin, C., Liu, Y., Dou, Z., Liu, L., Ma, Y., Zhang, S.-H., Habermann, M., Theobalt, C., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00951 · Cited by 377
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions
Haque, A., Tancik, M., Efros, A. A., Holynski, A., & Kanazawa, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01808 · Cited by 314
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Höllein, L., Cao, A., Owens, A., Johnson, J., & Nießner, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00727 · Cited by 167
Text2NeRF: Text-Driven 3D Scene Generation With Neural Radiance Fields
Zhang, J., Li, X., Wan, Z., Wang, C., & Liao, J. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3361502 · Cited by 94
Metadata
- Authors
- Wang, H., Du, X., Li, J., Yeh, R. A., & Shakhnarovich, G.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 12619-12629
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075859
- Cited by
- 343
- References
- 58
- FWCI
- 39.00
- 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
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.