Large pretrained diffusion models can provide strong priors beneficial for many graphics applications. However, generative applications such as neural rendering and inverse methods such as SVBRDF estimation and intrinsic image decomposition require additional input or output channels. Current solutions for channel expansion are often application specific and these solutions can be difficult to adapt to different diffusion models or new tasks. This paper introduces Teamwork: a flexible and efficient unified solution for jointly increasing the number of input and output channels as well as adapting a pretrained diffusion model to new tasks. Teamwork achieves channel expansion without altering the pretrained diffusion model architecture by coordinating and adapting multiple instances of the base diffusion model (i.e., teammates). We employ a novel variation of Low Rank-Adaptation (LoRA) to jointly address both adaptation and coordination between the different teammates. Furthermore Teamwork supports dynamic (de)activation of teammates. We demonstrate the flexibility and efficiency of Teamwork on a variety of generative and inverse graphics tasks such as inpainting, single image SVBRDF estimation, intrinsic decomposition, neural shading, and intrinsic image synthesis.

We present a novel and flexible learning-based method for generating tileable image sets. Our method goes beyond simple self-tiling, supporting sets of mutually tileable images that exhibit a high degree of diversity. To promote diversity we decouple structure from content by foregoing explicit copying of patches from an exemplar image. Instead we leverage the prior knowledge of natural images and textures embedded in large-scale pretrained diffusion models to guide tile generation constrained by exterior boundary conditions and a text prompt to specify the content. By carefully designing and selecting the exterior boundary conditions, we can reformulate the tile generation process as an inpainting problem, allowing us to directly employ existing diffusion-based inpainting models without the need to retrain a model on a custom training set. We demonstrate the flexibility and efficacy of our content-aware tile generation method on different tiling schemes, such as Wang tiles, from only a text prompt. Furthermore, we introduce a novel Dual Wang tiling scheme that provides greater texture continuity and diversity than existing Wang tile variants.

We formulate SVBRDF estimation from photographs as a diffusion task. To model the distribution of spatially varying materials, we first train a novel unconditional SVBRDF diffusion backbone model on a large set of 312, 165 synthetic spatially varying material exemplars. This SVBRDF diffusion backbone model, named MatFusion, can then serve as a basis for refining a conditional diffusion model to estimate the material properties from a photograph under controlled or uncontrolled lighting. Our backbone MatFusion model is trained using only a loss on the reflectance properties, and therefore refinement can be paired with more expensive rendering methods without the need for backpropagation during training. Because the conditional SVBRDF diffusion models are generative, we can synthesize multiple SVBRDF estimates from the same input photograph from which the user can select the one that best matches the users’ expectation. We demonstrate the flexibility of our method by refining different SVBRDF diffusion models conditioned on different types of incident lighting, and show that for a single photograph under colocated flash lighting our method achieves equal or better accuracy than existing SVBRDF estimation methods.