Taplio - Build a growth routine on LinkedIn
Mini toolsLiTo
By Apple
LiTo, short for Surface Light Field Tokenization, is an Apple research project accepted at ICLR 2026 for learning a compact 3D latent representation that jointly models object geometry and view-dependent appearance. It encodes random subsamples of RGB-depth surface light fields into latent vectors, allowing generated 3D objects to preserve lighting, material appearance, specular highlights, and Fresnel reflections from the input image. The repository provides a LiTo tokenizer and image-to-3D generative checkpoints, including recommended fixed versions, plus an interactive demo for Linux with NVIDIA GPUs and macOS Apple Silicon.
New
Multimodal
Gen 3
Overview
LiTo is Apple’s research image-to-3D model and tokenizer for generating 3D objects with unified geometry and view-dependent appearance.
Tools using LiTo
No tools found for this model yet.
Last updated: May 22, 2026
