Researchers have introduced Luce, a novel 3D representation designed for high-fidelity image-to-3D asset generation. Luce unifies geometry and physically based rendering (PBR) materials within a voxelized multimodal Gaussian cloud, enabling assets to be relit and integrated into standard rendering pipelines. The system utilizes a variational autoencoder for compression and a Rectified Flow transformer for generation from single images, demonstrating state-of-the-art performance on the Toys4K dataset and improving CLIP image-alignment scores on AI-generated images. AI
影响 Enhances 3D asset creation pipelines by enabling relightable and materially faithful assets from single images.
排序理由 The cluster describes a new academic paper detailing a novel method for 3D asset generation. [lever_c_demoted from research: ic=1 ai=1.0]
- Luce
- physically based rendering
- Rectified Flow transformer
- Toys4K
- variational auto-encoder
- voxelized multimodal Gaussian cloud
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
