用优化方法从一张图生成360度3D场景，更连贯真实。
PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion
- 将全景图与深度估计转为优化问题，交替求解
- 重建结果在一致性与质量上优于现有方法
- 适合需要高质量全景3D重建的科研与应用
本文提出PanoDreamer，一种从单张图像生成一致360° 3D场景的新方法。不同于现有逐段生成的方法，我们将问题建模为单图像全景图与深度估计任务。获得一致的全景图及其对应深度后，通过修复小范围遮挡区域并投影至3D空间完成场景重建。核心贡献在于将全景图与深度估计建模为两个优化问题，并引入交替最小化策略有效求解目标。实验表明，该方法在单图像360° 3D场景重建任务中，于一致性和整体质量方面均优于现有技术。
原文摘要 · Abstract (English)
In this paper, we present PanoDreamer, a novel method for producing a coherent 360° 3D scene from a single input image. Unlike existing methods that generate the scene sequentially, we frame the problem as single-image panorama and depth estimation. Once the coherent panoramic image and its corresponding depth are obtained, the scene can be reconstructed by inpainting the small occluded regions and projecting them into 3D space. Our key contribution is formulating single-image panorama and depth estimation as two optimization tasks and introducing alternating minimization strategies to effectively solve their objectives. We demonstrate that our approach outperforms existing techniques in single-image 360° 3D scene reconstruction in terms of consistency and overall quality.
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。