Abstract
Graphics pipelines require physically-based rendering (PBR) materials, yet current 3D content generation approaches are built on RGB models. We propose to model the PBR image distribution directly, avoiding photometric inaccuracies in RGB generation and the inherent ambiguity in extracting PBR from RGB. As existing paradigms for cross-modal fine-tuning are not suited for PBR generation due to both a lack of data and the high dimensionality of the output modalities, we propose to train a new PBR model that is tightly linked to a frozen RGB model using a novel cross-network communication paradigm. As the base RGB model is fully frozen, the proposed method retains its general performance and remains compatible with e.g. IPAdapters for that base model.
S. Vainer and S. Donné—Equal Contributions.
M. Boss—Stability AI, work done while at Unity Technologies.
Core Technical Contributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Our intuition as to why a fixed environment map is beneficial is that it makes the RGB model’s internal states more consistent to interpret, and makes the control problem of projecting to \(\textrm{Im}(f)\) simpler. Early in training, generated sample quality can be boosted significantly by applying the foreground mask to the RGB estimate for the first few timesteps; a rough projection to bring the estimate much closer to \(\textrm{Im}(f)\). After longer training, this is no longer necessary, as the PBR branch is capable enough to restrict the RGB branch to \(\textrm{Im}(f)\).
- 2.
References
Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. stat 1050, 21 (2016)
Burley, B.: Physically based shading at disney. ACM Trans. Graph. (SIGGRAPH) (2012)
Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: TexFusion: synthesizing 3D textures with text-guided image diffusion models. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4169–4181 (2023)
Chambon, T., Heitz, E., Belcour, L.: Passing multi-channel material textures to a 3-channel loss. In: ACM SIGGRAPH 2021 Talks, pp. 1–2 (2021)
Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nießner, M.: Text2Tex: text-driven texture synthesis via diffusion models. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 18558–18568 (2023)
Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 22246–22256 (2023)
Cook, R.L., Torrance, K.E.: A reflectance model for computer graphics. ACM Trans. Graph. (ToG) 1(1), 7–24 (1982)
Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142–13153 (2023)
Zavadski, D., Feiden, J.F., Rother, C.: ControlNet-XS: designing an efficient and effective architecture for controlling text-to-image diffusion models (2023)
Du, X., Kolkin, N., Shakhnarovich, G., Bhattad, A.: Intrinsic LoRA: a generalist approach for discovering knowledge in generative models. In: Synthetic Data for Computer Vision Workshop, CVPR 2024 (2024)
Duan, Y., Guo, X., Zhu, Z.: DiffusionDepth: diffusion denoising approach for monocular depth estimation. arXiv preprint arXiv:2303.05021 (2023)
Foong, T.Y., Kotyan, S., Mao, P.Y., Vargas, D.V.: The challenges of image generation models in generating multi-component images. arXiv preprint arXiv:2311.13620 (2023)
Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Guo, P., et al.: StableDreamer: taming noisy score distillation sampling for text-to-3D. arXiv preprint arXiv:2312.02189 (2023)
Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840–6851 (2020)
Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)
Hu, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8153–8163 (2024)
Huang, T., et al.: DreamControl: control-based text-to-3D generation with 3D self-prior. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5364–5373 (2024)
Huang, Y., Wang, J., Shi, Y., Qi, X., Zha, Z.J., Zhang, L.: DreamTime: an improved optimization strategy for text-to-3D content creation. arXiv preprint arXiv:2306.12422 (2023)
Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking FID: towards a better evaluation metric for image generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9307–9315 (2024)
Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. In: Advances in Neural Information Processing Systems, vol. 36 (2024)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
Karras, T., et al.: Alias-free generative adversarial networks. In: Advances in Neural Information Processing Systems, vol. 34, pp. 852–863 (2021)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110–8119 (2020)
Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492–9502 (2024)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Knodt, J., Gao, X.: Consistent mesh diffusion. arXiv preprint arXiv:2312.00971 (2023)
Le, C., Hetang, C., Cao, A., He, Y.: EucliDreamer: fast and high-quality texturing for 3D models with stable diffusion depth. arXiv preprint arXiv:2311.15573 (2023)
Lee, H.Y., Tseng, H.Y., Yang, M.H.: Exploiting diffusion prior for generalizable dense prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7861–7871 (2024)
Li, X., et al.: Advances in 3D generation: a survey. arXiv preprint arXiv:2401.17807 (2024)
Liang, Y., Yang, X., Lin, J., Li, H., Xu, X., Chen, Y.: LucidDreamer: towards high-fidelity text-to-3D generation via interval score matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6517–6526 (2024)
Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 5404–5411 (2024)
Liu, F., Wu, D., Wei, Y., Rao, Y., Duan, Y.: Sherpa3D: boosting high-fidelity text-to-3D generation via coarse 3D prior. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20763–20774 (2024)
Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9298–9309 (2023)
Liu, Y.T., Guo, Y.C., Luo, G., Sun, H., Yin, W., Zhang, S.H.: PI3D: efficient text-to-3D generation with pseudo-image diffusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19915–19924 (2024)
Liu, Z., et al.: UniDream: unifying diffusion priors for relightable text-to-3D generation. arXiv preprint arXiv:2312.08754 (2023)
Long, X., et al.: Wonder3D: single image to 3D using cross-domain diffusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9970–9980 (2024)
Ma, B., Deng, H., Zhou, J., Liu, Y.S., Huang, T., Wang, X.: GeoDream: disentangling 2D and geometric priors for high-fidelity and consistent 3D generation. arXiv preprint arXiv:2311.17971 (2023)
Ma, Y., et al.: X-Dreamer: creating high-quality 3D content by bridging the domain gap between text-to-2D and text-to-3D generation. arXiv preprint arXiv:2312.00085 (2023)
Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 4296–4304 (2024)
Van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al.: Conditional image generation with PixelCNN decoders. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: The Eleventh International Conference on Learning Representations (2023)
Raj, A., et al.: DreamBooth3D: subject-driven text-to-3D generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2349–2359 (2023)
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684–10695 (2022)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Sarkar, A., Mai, H., Mahapatra, A., Lazebnik, S., Forsyth, D.A., Bhattad, A.: Shadows don’t lie and lines can’t bend! Generative models don’t know projective geometry... for now. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 28140–28149 (2024)
Sartor, S., Peers, P.: MatFusion: a generative diffusion model for SVBRDF capture. In: SIGGRAPH Asia 2023 Conference Papers, SA 2023. ACM (2023). https://doi.org/10.1145/3610548.3618194
Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278–25294 (2022)
Sharma, P., et al.: Alchemist: parametric control of material properties with diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 24130–24141 (2024)
Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)
Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. In: The Twelfth International Conference on Learning Representations (2024)
Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256–2265. PMLR (2015)
Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)
Stan, G.B.M., et al.: LDM3D: latent diffusion model for 3D. arXiv preprint arXiv:2305.10853 (2023)
Subias, J.D., Lagunas, M.: In-the-wild material appearance editing using perceptual attributes. In: Computer Graphics Forum, vol. 42, pp. 333–345. Wiley Online Library (2023)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Tang, B., Wang, J., Wu, Z., Zhang, L.: Stable score distillation for high-quality 3D generation. arXiv preprint arXiv:2312.09305 (2023)
Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative gaussian splatting for efficient 3D content creation. In: The Twelfth International Conference on Learning Representations (2024)
Huggingface zerodiffusion model weights v0.9. https://huggingface.co/drhead. https://huggingface.co/drhead/ZeroDiffusion. Accessed 08 Feb 2024
Van Den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747–1756. PMLR (2016)
Vecchio, G., et al.: ControlMat: a controlled generative approach to material capture. arXiv preprint arXiv:2309.01700 (2023)
Wang, P., et al.: SteinDreamer: variance reduction for text-to-3D score distillation via stein identity. arXiv preprint arXiv:2401.00604 (2023)
Wang, Z., Li, M., Chen, C.: LucidDreaming: controllable object-centric 3D generation. arXiv preprint arXiv:2312.00588 (2023)
Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)
Wu, H., et al.: Q-Align: teaching LMMs for visual scoring via discrete text-defined levels. In: Forty-First International Conference on Machine Learning (2024)
Wu, T., et al.: HyperDreamer: hyper-realistic 3D content generation and editing from a single image. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1–10 (2023)
Wu, Z., Zhou, P., Yi, X., Yuan, X., Zhang, H.: Consistent3D: towards consistent high-fidelity text-to-3D generation with deterministic sampling prior. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9892–9902 (2024)
Xu, X., Lyu, Z., Pan, X., Dai, B.: MATLABER: material-aware text-to-3D via latent BRDF auto-encoder. arXiv preprint arXiv:2308.09278 (2023)
Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-Adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)
Yeh, Y.Y., et al.: TextureDreamer: image-guided texture synthesis through geometry-aware diffusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4304–4314 (2024)
Youwang, K., Oh, T.H., Pons-Moll, G.: Paint-it: text-to-texture synthesis via deep convolutional texture map optimization and physically-based rendering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4347–4356 (2024)
Yu, K., Liu, J., Feng, M., Cui, M., Xie, X.: Boosting3D: high-fidelity image-to-3D by boosting 2D diffusion prior to 3D prior with progressive learning. arXiv preprint arXiv:2311.13617 (2023)
Zeng, X., et al.: Paint3D: paint anything 3D with lighting-less texture diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4252–4262 (2024)
Zhang, J., et al.: Repaint123: fast and high-quality one image to 3D generation with progressive controllable 2D repainting. arXiv preprint arXiv:2312.13271 (2023)
Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3836–3847 (2023)
Zhou, L., Shih, A., Meng, C., Ermon, S.: DreamPropeller: supercharge text-to-3D generation with parallel sampling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4610–4619 (2024)
Zhuang, J., Wang, C., Lin, L., Liu, L., Li, G.: DreamEditor: text-driven 3D scene editing with neural fields. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1–10 (2023)
Acknowledgements
This work was supported fully by Unity Technologies, without external funding. We would like to thank the reviewers for their valuable feedback and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vainer, S. et al. (2025). Collaborative Control for Geometry-Conditioned PBR Image Generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15071. Springer, Cham. https://doi.org/10.1007/978-3-031-72624-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-72624-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72623-1
Online ISBN: 978-3-031-72624-8
eBook Packages: Computer ScienceComputer Science (R0)