用关键点优化相机位姿，高效重建汽车3D模型。
KRONC: Keypoint-based Robust Camera Optimization for 3D Car Reconstruction
- 基于物体语义关键点，轻量级优化相机位姿
- 仅需粗初始化即可达成高质量位姿估计
- 计算量远低于传统方法，适合实时场景
从图像集重建三维场景是长期研究的课题，尤其在NeRF方法流行后备受关注。然而，相机位姿（即外参）的准确估计常被忽视。尽管已有优秀的通用结构光流方法，但其计算开销大，且需大量重叠视角帧。本文提出KRONC，一种利用物体先验知识与语义关键点推断视图位姿的新方法，专注于车辆场景。通过将关键点反投影收敛至单点，求解轻量级优化问题以估计相机位置。为验证方法，构建了真实世界汽车场景数据集。实验表明，即使从粗略初始值出发，KRONC仍能生成优异的相机位姿估计，性能媲美结构光流方法，但计算成本大幅降低。代码与数据将公开。
原文摘要 · Abstract (English)
The three-dimensional representation of objects or scenes starting from a set of images has been a widely discussed topic for years and has gained additional attention after the diffusion of NeRF-based approaches. However, an underestimated prerequisite is the knowledge of camera poses or, more specifically, the estimation of the extrinsic calibration parameters. Although excellent general-purpose Structure-from-Motion methods are available as a pre-processing step, their computational load is high and they require a lot of frames to guarantee sufficient overlapping among the views. This paper introduces KRONC, a novel approach aimed at inferring view poses by leveraging prior knowledge about the object to reconstruct and its representation through semantic keypoints. With a focus on vehicle scenes, KRONC is able to estimate the position of the views as a solution to a light optimization problem targeting the convergence of keypoints' back-projections to a singular point. To validate the method, a specific dataset of real-world car scenes has been collected. Experiments confirm KRONC's ability to generate excellent estimates of camera poses starting from very coarse initialization. Results are comparable with Structure-from-Motion methods with huge savings in computation. Code and data will be made publicly available.
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。