PulseAugur
实时 06:44:39

New EAG-PT method reconstructs and edits indoor scenes with diffuse global illumination

Researchers have developed EAG-PT, a novel method for reconstructing and editing indoor scenes with diffuse global illumination. This approach utilizes 2D Gaussians as a geometric proxy, bypassing the need for explicit mesh reconstruction. EAG-PT separates emissive and non-emissive components, enabling easier scene editing, and decouples reconstruction from rendering through optimization and path tracing. The method demonstrates improved physical consistency and detail preservation compared to existing radiance-field and mesh-based techniques, showing promise for applications in interior design and XR content creation. AI

影响 Enhances capabilities for realistic scene editing and reconstruction, potentially impacting AR/VR and design applications.

排序理由 This is a research paper detailing a new method for scene reconstruction and editing.

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

New EAG-PT method reconstructs and edits indoor scenes with diffuse global illumination

报道来源 [1]

  1. arXiv cs.CV TIER_1 English(EN) · Xijie Yang, Mulin Yu, Changjian Jiang, Kerui Ren, Tao Lu, Jiangmiao Pang, Dahua Lin, Bo Dai, Linning Xu ·

    EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

    arXiv:2601.23065v2 Announce Type: replace-cross Abstract: Recent radiance-field-based reconstruction methods, such as NeRF and 3DGS, achieve high visual fidelity for indoor scenes, but often break down under scene editing due to baked illumination and the lack of explicit light t…