仅用2-8张无标定图像，快速重建3D结构与相机位姿。
FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
- 分阶段推断：先估相机位姿，再基于位姿重建几何与外观。
- 在2-8张稀疏视图下实现顶尖的三维重建与新视角生成效果。
- 推理速度低于0.5秒，适合实时应用，如移动设备或AR场景。
我们提出FLARE，一种前馈模型，可从少量未标定视图（最少2-8张）中高精度推断相机位姿与3D几何结构，该设置在真实场景中极具挑战性但又十分实用。方法采用级联学习范式，以相机位姿为关键桥梁，因其在将3D结构映射到2D图像平面中的核心作用。具体而言，FLARE首先进行相机位姿估计，其结果用于引导后续几何结构与外观的建模，并通过几何重建和新视角合成的目标进行优化。基于大规模公开数据集训练，本方法在相机位姿估计、几何重建和新视角合成任务上均达到当前最优性能，且推理时间低于0.5秒。项目主页与代码详见：https://zhanghe3z.github.io/FLARE/
原文摘要 · Abstract (English)
We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/
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。