Apple announces LiTo technology: capable of reconstructing complete 3D objects from a single image while preserving lighting and shadow consistency

Gate News: On March 17, Apple’s AI research team published a paper at ICLR 2026 introducing a 3D generation method called LiTo (Surface Light Field Tokenization). It can generate complete 3D objects from a single image and maintain consistent lighting effects such as specular highlights and Fresnel reflections when changing viewpoints. Previously, most 3D reconstruction methods could only handle either geometry or diffuse appearance, making it difficult to restore view-dependent lighting details. LiTo encodes object geometry and view-dependent appearance into a unified 3D latent space, then uses a latent flow matching model to generate results from a single image. The training data consists of thousands of 3D objects, each rendered from 150 viewpoints under three lighting conditions. The decoder learns to reconstruct full geometry and appearance by randomly sampling sub-sets. Experiments show that LiTo outperforms existing methods like TRELLIS in visual quality and fidelity to input images. The paper is authored by Jen-Hao Rick Chang, Xiaoming Zhao (co-first author), Dorian Chan, and Oncel Tuzel, and is publicly available on arXiv.