3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

翻译：三维高斯泼溅（3D-GS）已成为一种高效的三维表示方法，并为语义分割等任务提供了有前景的基础。然而，现有基于3D-GS的分割方法通常依赖于高维类别特征，这带来了显著的内存开销。此外，由于标签空间拥挤以及缺乏稳定的多粒度控制机制，细粒度分割仍面临挑战。为克服这些局限，我们提出了一种从粗到细的二进制编码方案，用于每个高斯单元的类别表示，通过二进制到十进制的映射将每个特征压缩为单个整数，从而大幅降低内存占用。我们进一步设计了一种渐进式训练策略，将全景分割分解为一系列独立的子任务，减少了类间冲突，从而提升了细粒度分割能力。此外，我们在分割训练期间微调不透明度，以解决光度渲染与语义分割之间的不兼容性问题，该问题常导致前景与背景混淆。在多个基准数据集上的大量实验表明，我们的方法在显著降低内存消耗并加速推理的同时，实现了最先进的分割性能。