MEt3R: Measuring Multi-View Consistency in Generated Images
This addresses the need for independent metrics in multi-view image generation for researchers and practitioners, though it is incremental as it builds on existing reconstruction techniques.
The authors tackled the problem of measuring multi-view consistency in generated images by introducing MEt3R, a metric that uses dense 3D reconstructions and feature comparisons to assess consistency independently of the scene, and they applied it to evaluate various methods including their own latent diffusion model.
We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inference from sparse observations. However, due to the nature of generative modeling, traditional reconstruction metrics are not suitable to measure the quality of generated outputs and metrics that are independent of the sampling procedure are desperately needed. In this work, we specifically address the aspect of consistency between generated multi-view images, which can be evaluated independently of the specific scene. Our approach uses DUSt3R to obtain dense 3D reconstructions from image pairs in a feed-forward manner, which are used to warp image contents from one view into the other. Then, feature maps of these images are compared to obtain a similarity score that is invariant to view-dependent effects. Using MEt3R, we evaluate the consistency of a large set of previous methods for novel view and video generation, including our open, multi-view latent diffusion model.