用深度引导分组采样，加速神经辐射场渲染并提升画质。
Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
- 将相邻光线分组采样，共享解码表示，减少冗余计算。
- 在DTU数据集上提升1.27 dB PSNR，帧率提高47%。
- 适合需要高效高质3D重建的视觉生成应用。
通用新视角合成近期通过邻近视角插值取得了显著质量提升，但高分辨率图像渲染仍因需密集采样所有光线而计算成本高昂。鉴于自然场景通常具有分片平滑特性，全光线采样常显冗余。本文提出一种深度引导的束采样策略，将相邻光线分组并集体采样，为束内所有光线生成共享表示。为进一步优化效率，自适应采样策略根据深度置信度动态分配样本，复杂区域增加采样，平滑区域减少采样。应用于ENeRF时，该方法在DTU数据集上实现最高1.27 dB的PSNR提升和47%的帧率增长。在合成与真实世界数据集上的广泛实验表明，其渲染质量达当前最优水平，相比现有通用方法最高提速2倍。代码已公开于https://github.com/KLMAV-CUC/GDB-NeRF。
原文摘要 · Abstract (English)
Recent advancements in generalizable novel view synthesis have achieved impressive quality through interpolation between nearby views. However, rendering high-resolution images remains computationally intensive due to the need for dense sampling of all rays. Recognizing that natural scenes are typically piecewise smooth and sampling all rays is often redundant, we propose a novel depth-guided bundle sampling strategy to accelerate rendering. By grouping adjacent rays into a bundle and sampling them collectively, a shared representation is generated for decoding all rays within the bundle. To further optimize efficiency, our adaptive sampling strategy dynamically allocates samples based on depth confidence, concentrating more samples in complex regions while reducing them in smoother areas. When applied to ENeRF, our method achieves up to a 1.27 dB PSNR improvement and a 47% increase in FPS on the DTU dataset. Extensive experiments on synthetic and real-world datasets demonstrate state-of-the-art rendering quality and up to 2x faster rendering compared to existing generalizable methods. Code is available at https://github.com/KLMAV-CUC/GDB-NeRF.
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。