从稀疏360°图像重建高精度车辆3D模型，适合实际场景应用。
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images
- 用深度图与鲁棒位姿估计提升稀疏视角下的重建质量
- 在多个基准上达到当前最优，稀疏输入下仍保持高保真度
- 新数据集含真实与合成公交车辆，推动真实场景评估
准确的车辆3D重建对车辆检测、预测性维护和城市规划至关重要。现有方法如神经辐射场（Neural Radiance Fields）和高斯溅射（Gaussian Splatting）虽表现优异，但依赖密集视角输入，限制了实际应用。本文针对稀疏视角输入下的车辆3D重建挑战，结合深度图与鲁棒位姿估计架构，实现新视角合成与训练数据增强。具体而言，通过仅对高置信度像素应用选择性光度损失，改进高斯溅射；并以DUSt3R架构替代传统运动结构（Structure-from-Motion）流程，提升相机位姿估计精度。此外，我们构建了一个包含合成与真实公共交通车辆的新数据集，支持全面评估。实验表明，该方法在多个基准上均达领先性能，即使在输入受限条件下也能实现高质量重建。
原文摘要 · Abstract (English)
Accurate 3D reconstruction of vehicles is vital for applications such as vehicle inspection, predictive maintenance, and urban planning. Existing methods like Neural Radiance Fields and Gaussian Splatting have shown impressive results but remain limited by their reliance on dense input views, which hinders real-world applicability. This paper addresses the challenge of reconstructing vehicles from sparse-view inputs, leveraging depth maps and a robust pose estimation architecture to synthesize novel views and augment training data. Specifically, we enhance Gaussian Splatting by integrating a selective photometric loss, applied only to high-confidence pixels, and replacing standard Structure-from-Motion pipelines with the DUSt3R architecture to improve camera pose estimation. Furthermore, we present a novel dataset featuring both synthetic and real-world public transportation vehicles, enabling extensive evaluation of our approach. Experimental results demonstrate state-of-the-art performance across multiple benchmarks, showcasing the method's ability to achieve high-quality reconstructions even under constrained input conditions.
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。