发表机构
Quidient（奎迪恩特）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出全光凝聚（PCon）的广义场景重建新方法，通过多阶段管道转换和凝聚场景元素，其现实模型实现空间变化表征能力。实验表明该方法在重建精度上超现有先进方法，如在“受损菲亚特”案例中能精准测量损伤，优于对比方法。
AI 中文摘要
我们提出了一种名为全光凝聚（PCon）的新型广义场景重建（GSR）方法。PCon采用多阶段重建管道，先将图像转换为低（表征）能力的“汤状”场景元素，再自适应地将“汤”凝聚为高能力的“结构化”元素，如锐利边缘和平滑反射表面。PCon的场景模型——现实模型（Relms）实现空间变化的表征能力，对高保真渲染、测量和场景理解至关重要。我们展示了用消费级手机相机和无人机拍摄的多个PCon野外重建实例。在“受损菲亚特”案例中，PCon与两种先进的GSR方法NeRO和RT - Splatting进行基准测试。结果显示，PCon重建汽车引擎盖的精度是先进方法的两倍多，且PCon的局部损伤轮廓误差为35微米（0.035毫米），而其他两种先进方法基本无法测量损伤。
英文摘要
We present a novel Generalized Scene Reconstruction (GSR) approach called Plenoptic Condensation (PCon). PCon uses a multi-stage reconstruction pipeline, initially converting images into "soupy" scene elements with low (representational) power, then adaptively condensing the "soup" into "structured" elements of higher power capable of efficiently representing, for example, sharp edges and smooth reflective surfaces. PCon scene models called Reality Models (Relms) enable spatially varying representational power, which is essential for high-fidelity rendering, measurement, and scene understanding. We showcase several in-the-wild PCon reconstructions captured with consumer phone cameras and drones. In one case called "Damaged Fiat", PCon is benchmarked against two state-of-the-art (SOTA) GSR methods: NeRO and RT-Splatting. Referring to Figure 1 below, PCon reconstructs the car hood more than twice as accurately as the SOTA methods. But more importantly, the local damage profile error for PCon is 35 um (0.035 mm), whereas the two other SOTA methods are essentially unable to measure the damage at all. Our project website is available at https://quidient.github.io/pcon-2026.html.
