Dynamic optimization loop aligns 3D generators with 2D diffusion priors to improve realism

OREO uses on-the-fly rendered-view editing and reinforced learning to refine 3D assets from pre-trained models without static datasets.

Chinese Tech

The Hong Kong Polytechnic University · Tencent ARC Lab

Research Digest·3 October 2026·2 min read

The authors propose OREO, a framework that enhances visual fidelity of 3D generators by creating a dynamic optimization loop.

Ma et al.

Why this paper

From Tencent ARC Lab and The Hong Kong Polytechnic University

OREO enhances 3D generation fidelity by editing rendered views and distilling the gap back into the generator via latent contrastive learning.

Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.