Oliver Haslam on December 18, 2025, 9:50 pm

Apple Released A New Open-Source 2D To 3D Photo Model

Apple has released a new open-source model that can instantly turn your 2D photos into 3D views.

Dubbed SHARP, the new model was released as part of a published study titled Sharp Monocular View Synthesis in Less Than a Second.

The study explains how Apple trained the model to create a 3D scene from a single 2D image. It does that while keeping distances and scale consistent.

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.

The explanation of how this works is, as you’d expect, detailed and complicated. But there are some posts on X that show SHARP’s work, and they’re impressive considering what’s being used.

This 2D to 3D image creation is similar to that already available via some Apple devices, with the resulting image looking its best when viewed on an Apple Vision Pro. In some instances, users have turned the resulting 3D scene into a video for playback elsewhere, too.