EscherNet: A Generative Model for Scalable View Synthesis

TL;DR

EscherNet is a scalable generative model that synthesizes multiple novel views from limited reference images, unifying 3D reconstruction and view synthesis with state-of-the-art performance on various benchmarks.

Contribution

Introduces EscherNet, a versatile diffusion-based model capable of generating numerous consistent views and unifying 3D reconstruction with view synthesis tasks.

Findings

Generates over 100 views simultaneously on a single GPU.

Achieves state-of-the-art results across multiple benchmarks.

Unifies single- and multi-image 3D reconstruction tasks.

Abstract

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.