← Back to all news
arXiv Computer Vision By Zhiyuan Ma, Wenbo Hu, Wang Zhao, Pengfei Wang, Ying Shan, Lei Zhang

OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization

Read the original on arXiv Computer Vision →

OREO is a framework that improves the visual fidelity of 3D generation models by using on-the-fly rendered and edited 2D views as pseudo-targets. It introduces a dynamic optimization loop where a 2D diffusion model refines rendered views, preserving geometry, viewpoint, and content while enhancing realism. These refined views serve as high‑quality supervision, enabling the 3D generator to learn from its own outputs and progressively improve its visual quality, outperforming pre‑trained baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 7

Learning 3D Editing without Paired Supervision via Generative Prior Distillation

The paper introduces a framework for instruction‑guided 3D editing that does not require paired 3D supervision. It distills visual, semantic, and geometric knowledge from foundation models into a 3D editing model using a differentiable rendering pipeline, guided by a 2D visual prior from an image editing model and a semantic prior from a Vision‑Language Model. A 3D‑aware Distribution Matching regularization is added to prevent geometric collapse and ensure realistic 3D outputs, leading to superior instruction fidelity and cross‑view consistency compared to state‑of‑the‑art baselines.

By Hao Wen, Weibin Yun, Hongxing Fan, Haotian Lu, Rui Chen, Zehuan Huang, Lu Sheng
llmsdiffusionefficiencymultimodalbenchmarks
More like this →