以更短高斯列表加速三维高斯学习
Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
通过定期重置高斯尺度并沿射线对 alpha 混合权重施加熵约束，缩短每个像素的高斯列表长度，可直接嵌入现有 3DGS 训练流程以降低泼溅渲染开销；该思路也可迁移到其他基于射线采样的表示（如神经辐射场）的加速。
原文依据 we introduce an entropy constraint on the alpha blending procedure to sharpen the weight distribution of Gaussians along each ray
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）已成为从多张带位姿图像学习辐射场的重要工具。尽管 3DGS 在渲染质量与效率上相较神经辐射场展现出显著优势，进一步提升三维高斯学习效率仍是一个研究难题。为应对该挑战，我们提出新的训练策略与损失，以缩短渲染每个像素所用的高斯列表，从而通过沿射线涉及更少的高斯来加速泼溅。具体而言，我们通过定期重置高斯的尺度来缩小每个高斯的大小，促使较小的高斯覆盖更少的邻近像素，从而缩短像素的高斯列表。此外，我们在 alpha 混合过程中引入熵约束，以锐化沿每条射线的高斯权重分布，使主导权重更大、次要权重更小。由此，每个高斯更专注于其占主导的像素，减少其对邻近像素的影响，进一步缩短高斯列表。最终，我们将该方法集成到渲染分辨率调度器中，通过渐进式提高分辨率进一步提升效率。我们在广泛使用的基准上与最优方法进行比较以评估本方法。结果表明，在不牺牲渲染质量的前提下，本方法在效率上相较其他方法具有显著优势。
英文原文摘要 1424 字符
3D Gaussian splatting (3DGS) has become a vital tool for learning a radiance field from multiple posed images. Although 3DGS shows great advantages over NeRF in terms of rendering quality and efficiency, it remains a research challenge to further improve the efficiency of learning 3D Gaussians. To overcome this challenge, we propose novel training strategies and losses to shorten each Gaussian list used to render a pixel, which speeds up the splatting by involving fewer Gaussians along a ray. Specifically, we shrink the size of each Gaussian by resetting their scales regularly, encouraging smaller Gaussians to cover fewer nearby pixels, which shortens the Gaussian lists of pixels. Additionally, we introduce an entropy constraint on the alpha blending procedure to sharpen the weight distribution of Gaussians along each ray, which drives dominant weights larger while making minor weights smaller. As a result, each Gaussian becomes more focused on the pixels where it is dominant, which reduces its impact on nearby pixels, leading to even shorter Gaussian lists. Eventually, we integrate our method into a rendering resolution scheduler which further improves efficiency through progressive resolution increase. We evaluate our method by comparing it with state-of-the-art methods on widely used benchmarks. Our results show significant advantages over others in efficiency without sacrificing rendering quality.