提出球面注意力与新上采样方法，压缩效率提升23.1%。
OSLO-IC: On-the-Sphere Learned Omnidirectional Image Compression with Attention Modules and Spatial Context
- 引入球面注意力模块与空间自回归上下文模型
- 比特率降低23.1%（WS-PSNR BD rate），参数减少4倍
- 适合虚拟现实、自动驾驶等球面图像应用
开发高效的360度（球面）图像压缩技术对虚拟现实和自动驾驶等技术至关重要。本文通过提出球面注意力模块、残差块和空间自回归上下文模型，推进了球面学习（OSLO）在全景图像压缩框架中的进展。该改进使WS-PSNR的比特率降低了23.1%。此外，我们引入了一种球面转置卷积算子用于上采样，相比原OSLO框架中的像素洗牌方法，可将可训练参数减少4倍，同时保持相近的压缩性能。因此，所提方法在更小的模型规模下实现显著的码率节省，适用于任何球面卷积应用场景。
原文摘要 · Abstract (English)
Developing effective 360-degree (spherical) image compression techniques is crucial for technologies like virtual reality and automated driving. This paper advances the state-of-the-art in on-the-sphere learning (OSLO) for omnidirectional image compression framework by proposing spherical attention modules, residual blocks, and a spatial autoregressive context model. These improvements achieve a 23.1% bit rate reduction in terms of WS-PSNR BD rate. Additionally, we introduce a spherical transposed convolution operator for upsampling, which reduces trainable parameters by a factor of four compared to the pixel shuffling used in the OSLO framework, while maintaining similar compression performance. Therefore, in total, our proposed method offers significant rate savings with a smaller architecture and can be applied to any spherical convolutional application.
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。