Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
This addresses the problem of extracting meaningful internal representations from diffusion models for researchers and practitioners in computer vision, enabling better semantic correspondence in images.
The authors tackled the challenge of extracting useful feature descriptors from diffusion models, which are spread across layers and timesteps, by proposing Diffusion Hyperfeatures to consolidate these into per-pixel descriptors for downstream tasks. Their method achieved superior performance on the SPair-71k real image benchmark for semantic keypoint correspondence.
Diffusion models have been shown to be capable of generating high-quality images, suggesting that they could contain meaningful internal representations. Unfortunately, the feature maps that encode a diffusion model's internal information are spread not only over layers of the network, but also over diffusion timesteps, making it challenging to extract useful descriptors. We propose Diffusion Hyperfeatures, a framework for consolidating multi-scale and multi-timestep feature maps into per-pixel feature descriptors that can be used for downstream tasks. These descriptors can be extracted for both synthetic and real images using the generation and inversion processes. We evaluate the utility of our Diffusion Hyperfeatures on the task of semantic keypoint correspondence: our method achieves superior performance on the SPair-71k real image benchmark. We also demonstrate that our method is flexible and transferable: our feature aggregation network trained on the inversion features of real image pairs can be used on the generation features of synthetic image pairs with unseen objects and compositions. Our code is available at https://diffusion-hyperfeatures.github.io.