用网络摄像头构建可随季节变化的3D景观，支持重光照与修复。
SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams
- 基于8.5万张图像和32个地点，构建覆盖50×60km的季节性3D景观
- 通过条件扩散模型修复遮挡与缺失数据，实现完整网格重建
- 生成结果可接入物理渲染器，支持任意光照条件下的可视化
我们提出SeasonScapes框架与数据集：瑞士稀疏视角山地场景的季节变化数据集，覆盖50公里×60公里区域，包含来自32个位置、13个时间点（全年）的超过8.5万张网络摄像头图像。通过将各时间戳图像投影至3D网格，构建反映自然外观随时间演变的季节性3D景观。为解决遮挡与数据缺失问题，采用条件扩散模型在网格上进行图像引导的补全。最终生成的完整网格可进一步使用标准物理渲染器进行重光照。
原文摘要 · Abstract (English)
We introduce SeasonScapes framework and a the SeasonScapes dataset: Swiss Sparse-view Mountain Scenes with Seasonal Changes that covers over 50 km x 60 km, composed of more than 85,000 webcam images captured from 32 different locations across 13 timestamps throughout a full year. By projecting these timestamp-specific images onto a 3D mesh, we construct seasonal 3D landscapes that reflect natural appearance changes over time. To address occlusions and missing data, we leverage conditional diffusion models for image-guided inpainting directly on the mesh. The resulting completed meshes can be further relighted using standard physically-based renderer.
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。