用轻量级光场探针提升神经表面重建速度与精度
ProbeSDF: Light Field Probes for Neural Surface Reconstruction
- 用双分辨率体网格分离角度与空间特征，仅需4参数/体素
- 在真实数据上实现更快训练、实时渲染，PSNR与表面精度均提升
- 适用于物体与人像重建，适合需要高效3D建模的场景
基于SDF的微分渲染框架在多视角3D形状重建中达到顶尖水平。本文通过最小化重构其核心外观模型，同时实现更快计算和更高性能。我们提出一种物理启发的极简辐射率参数化方法，将角度与空间贡献解耦，分别用两个不同分辨率的体网格存储少量特征。每个体素仅需4个参数，且在单一融合核内仅调用一次小型MLP，显著提升性能与训练速度，并支持实时渲染。我们在四个具有挑战性的数据集上验证了该方法在通用物体与人体重建两个主流应用领域的稳定性表现。
原文摘要 · Abstract (English)
SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction. In this work, we re-examine this family of approaches by minimally reformulating its core appearance model in a way that simultaneously yields faster computation and increased performance. To this goal, we exhibit a physically-inspired minimal radiance parametrization decoupling angular and spatial contributions, by encoding them with a small number of features stored in two respective volumetric grids of different resolutions. Requiring as little as four parameters per voxel, and a tiny MLP call inside a single fully fused kernel, our approach allows to enhance performance with both surface and image (PSNR) metrics, while providing a significant training speedup and real-time rendering. We show this performance to be consistently achieved on real data over two widely different and popular application fields, generic object and human subject shape reconstruction, using four representative and challenging datasets.
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。