深度引导的束采样用于高效可泛化神经辐射场重建
Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
AI总结：
针对可泛化神经辐射场渲染计算量大、采样冗余的问题，提出深度引导的束采样策略，通过分组采样和自适应分配采样点，在DTU数据集上实现1.27 dB PSNR提升和47% FPS增加，并达到2倍渲染加速。
摘要：
近年来，可泛化的新视角合成通过相邻视角之间的插值取得了令人印象深刻的画质。然而，由于需要对所有光线进行密集采样，渲染高分辨率图像仍然计算量大。鉴于自然场景通常是分段平滑的，对所有光线进行采样往往是冗余的，我们提出了一种新颖的深度引导束采样策略来加速渲染。通过将相邻光线分组为一个束并对其进行集体采样，生成一个共享表示用于解码束内的所有光线。为了进一步优化效率，我们的自适应采样策略根据深度置信度动态分配采样点，在复杂区域集中更多采样点，同时在较平滑区域减少采样点。当应用于ENeRF时，我们的方法在DTU数据集上实现了高达1.27 dB的PSNR提升和47%的FPS增加。在合成和真实世界数据集上的大量实验表明，与现有可泛化方法相比，我们的方法实现了最先进的渲染质量和高达2倍的渲染加速。代码可在https://github.com/KLMAV-CUC/GDB-NeRF获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
