EscherNet: A Generative Model for Scalable View Synthesis
This work addresses the challenge of scalable and versatile 3D vision tasks, such as novel view synthesis and 3D reconstruction, for researchers and practitioners in computer vision, though it builds incrementally on existing diffusion and view synthesis methods.
The authors tackled the problem of scalable view synthesis by introducing EscherNet, a multi-view conditioned diffusion model that can generate over 100 consistent target views simultaneously on a consumer-grade GPU, achieving state-of-the-art performance across multiple benchmarks.
We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis. EscherNet learns implicit and generative 3D representations coupled with a specialised camera positional encoding, allowing precise and continuous relative control of the camera transformation between an arbitrary number of reference and target views. EscherNet offers exceptional generality, flexibility, and scalability in view synthesis -- it can generate more than 100 consistent target views simultaneously on a single consumer-grade GPU, despite being trained with a fixed number of 3 reference views to 3 target views. As a result, EscherNet not only addresses zero-shot novel view synthesis, but also naturally unifies single- and multi-image 3D reconstruction, combining these diverse tasks into a single, cohesive framework. Our extensive experiments demonstrate that EscherNet achieves state-of-the-art performance in multiple benchmarks, even when compared to methods specifically tailored for each individual problem. This remarkable versatility opens up new directions for designing scalable neural architectures for 3D vision. Project page: https://kxhit.github.io/EscherNet.