发表机构
Harbin Institute of Technology, Shenzhen; Shenzhen University（哈尔滨工业大学（深圳）; 深圳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出OIC-GS全向高斯泼溅编解码器，采用分层HEALPix网格表示和率失真优化，自适应选择基元，实现高质量快速解码，显著降低码率。
AI 中文摘要
学习型图像编解码器（LICs）能够实现高质量的重建，但其解码速度通常不足以支持沉浸式虚拟现实（VR）。高斯泼溅（GS）编解码器渲染速度更快，但在重建质量上仍有所欠缺，并且通常在分配基元时不考虑每个基元的编码成本。我们提出了OIC-GS，一种全向GS编解码器，采用新的分层HEALPix基元网格表示。高斯基元被锚定在预定义的球面位置上，从而消除了显式坐标编码。更精细的层级细化其更粗糙的祖先，自然支持从粗到细的重建和分层传输。预定义的网格还通过仅选择与视口相关的基元来实现高效的视口解码。我们进一步为量化基元引入了一个轻量级熵模型，并在球面率失真目标下优化编解码器。当量化不透明度变为零时，率失真收益不足的基元会被自动移除，使OIC-GS能够自适应基元密度和细节层次，而无需固定的基元预算。单个比特流支持全球、视口相关和渐进解码。第一个视口在解码仅52%的比特流后达到最终质量，并以1,270 FPS渲染。在100张图像的全向基准测试中，OIC-GS在所有评估的GS编解码器中表现最佳，相比GaussianImage++，WS-PSNR BD-rate降低了49.6%，相比使用学习熵模型的SGI，降低了68.6%。
英文摘要
Learned image codecs (LICs) achieve high reconstruction quality, but their decoding speed is often insufficient for immersive virtual reality (VR). Gaussian splatting (GS) codecs render much faster, yet still lag in reconstruction quality and typically decide primitive allocation without considering the coding cost of each primitive. We introduce OIC-GS, an omnidirectional GS codec with a new hierarchical HEALPix primitive grid representation. Gaussian primitives are anchored at predefined spherical locations, eliminating explicit coordinate coding. Finer levels refine their coarser ancestors, naturally supporting coarse-to-fine reconstruction and layered transmission. The predefined grid also enables efficient viewport decoding by selecting only view-relevant primitives. We further introduce a lightweight entropy model for quantized primitives and optimize the codec under a spherical rate-distortion objective. Primitives with insufficient rate-distortion benefit are automatically removed when their quantized opacity becomes zero, allowing OIC-GS to adapt both primitive density and level of detail without a fixed primitive budget. A single bitstream supports full-sphere, viewport-dependent, and progressive decoding. The first viewport reaches final quality after decoding only 52% of the bitstream, and is then rendered at 1,270 FPS. On a 100-image omnidirectional benchmark, OIC-GS outperforms all evaluated GS codecs, reducing WS-PSNR BD-rate by 49.6% over GaussianImage++ and 68.6% over SGI, which uses a learned entropy model.
Comments30 pages, 13 figures, 14 tables
