用分阶段压缩法重建高精度场景，能精准捕捉细微损伤。
Plenoptic Condensation: A Novel Approach to Generalized Scene Reconstruction
- 将图像转为低精度元素，再自适应压缩成高精度结构化表示
- 在真实场景中重建车体损伤，误差仅35微米，优于现有方法
- 适合需要高保真渲染与微观测量的应用，如工业检测
我们提出一种新型通用场景重建方法Plenoptic Condensation（PCon）。PCon采用多阶段重建流程，先将图像转化为低表征力的“汤状”场景元素，再自适应地将其压缩为具有更高表征力的“结构化”元素，可高效表达锐利边缘和光滑反光表面。所生成的场景模型称为现实模型（Relms），支持空间变化的表征力，对高保真渲染、测量与场景理解至关重要。我们在消费级手机与无人机拍摄的真实场景中展示了PCon的重建效果。在名为“受损菲亚特”的案例中，与两种先进方法NeRO和RT-Splatting对比，PCon对车盖的重建精度超过后者两倍；更重要的是，其局部损伤测量误差仅为35微米（0.035毫米），而其他两种方法几乎无法识别损伤。
原文摘要 · Abstract (English)
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.
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。