让3D生成模型直接理解光照条件，生成更真实可重打光的3D物体。
MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion
- 将光照条件融入多视角扩散模型，显式控制生成过程。
- 在多个视角下生成符合指定光照的真实图像，提升3D质量。
- 适合需要高保真3D内容与灵活重打光的应用场景。
近年来，基于高性能文本到图像生成模型的文本到3D生成技术，已能从文本描述中创建富有想象力且纹理丰富的3D物体。然而，如何有效解耦与光照无关和依赖光照的成分，仍是一大挑战，影响生成3D模型的质量与重打光能力。本文提出MVLight，一种新的光照条件多视角扩散模型，将光照条件直接整合进生成流程，使模型能在多个相机视角下合成忠实反映指定光照环境的高质量图像。通过利用该能力进行得分蒸馏采样（Score Distillation Sampling, SDS），我们有效提升了生成3D模型的几何精度与重打光性能。通过大量实验与用户研究验证了MVLight的有效性。
原文摘要 · Abstract (English)
Recent advancements in text-to-3D generation, building on the success of high-performance text-to-image generative models, have made it possible to create imaginative and richly textured 3D objects from textual descriptions. However, a key challenge remains in effectively decoupling light-independent and lighting-dependent components to enhance the quality of generated 3D models and their relighting performance. In this paper, we present MVLight, a novel light-conditioned multi-view diffusion model that explicitly integrates lighting conditions directly into the generation process. This enables the model to synthesize high-quality images that faithfully reflect the specified lighting environment across multiple camera views. By leveraging this capability to Score Distillation Sampling (SDS), we can effectively synthesize 3D models with improved geometric precision and relighting capabilities. We validate the effectiveness of MVLight through extensive experiments and a user study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。