Apple’s new open-source model can instantly turn 2D photos into 3D views

Apple is reportedly training a model to reconstruct a 3D scene from a single 2D image, while keeping distances and scale consistent in real-world terms. Apple detailed this model in its study titled Sharp Monocular View Synthesis in Less Than a Second.

The model can predict a 3D representation of a single image, which can be rendered from nearby viewpoints. 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.

Apple’s researchers in its study said, “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.”