Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
mlboydaisuke 
posted an update 9 days ago
Post
4,809
Turn one photo into a 3D object you can spin around, sides and back included, entirely on your phone.

On a Galaxy S26, Idol (speridlabs) on LiteRT now makes a splat of 65,536 Gaussians in 158 s with its new default form, or of 262,144 Gaussians in 267 s with the first release's form, which stays in the repo (the first photo after start, on a cool phone). Checked against the author's PyTorch pipeline, renders from four sides agree at a PSNR of 32.3–34.4 dB for the default and 41.4–46.6 dB for the larger form.

Graphs, a Python runner and an Android sample: litert-community/Idol

Wow bro

One check on the PSNR: 32–34 dB against the author's PyTorch pipeline measures agreement with the reference implementation, not fidelity to the input photo. Does the four-side comparison include a view the splat wasn't trained on?

·

Yes, all four: the views show the object's front, both sides and back, and none of them is from the input image's own viewpoint. Idol generates the splat from that single image rather than training it on views, so the sides the image does not show are generated too.

You are right that the number measures agreement with the reference. At every view, the back included, we compare the phone's splat of 65,536 Gaussians with the splat of 262,144 that the author's PyTorch pipeline generates from the same input image and the same random numbers, both rendered by the same renderer from the same cameras. The back view agrees at 33.04–35.05 dB over the three test inputs that gave the 32–34 dB. Fidelity to the input image, or to the real object's back, was not measured.

🔥