Sharp Monocular View Synthesis in Less Than a Second
This addresses the need for fast, high-quality monocular view synthesis for applications like virtual reality or content creation, representing a significant advance over previous methods.
The paper tackles the problem of photorealistic view synthesis from a single image by introducing SHARP, which regresses parameters for a 3D Gaussian representation in under a second, achieving state-of-the-art results with reductions in LPIPS by 25-34% and DISTS by 21-43% compared to prior models.
We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Experimental results demonstrate that SHARP delivers robust zero-shot generalization across datasets. It sets a new state of the art on multiple datasets, reducing LPIPS by 25-34% and DISTS by 21-43% versus the best prior model, while lowering the synthesis time by three orders of magnitude. Code and weights are provided at https://github.com/apple/ml-sharp