AI 中文总结
SphereSOD通过耦合球面几何与显著结构，在ERP空间直接进行可变形采样和结构引导解码，实现360度显著目标检测，在三个基准上达到最先进性能并兼顾效率。
AI 中文摘要
360度显著目标检测（SOD）旨在全视场范围内准确分割显著区域。然而，等距柱状投影（ERP）在将球面域映射到平面表示时引入了严重的空间畸变。现有方法主要侧重于补偿投影畸变，而忽视了在特征感知和预测细化过程中全景几何与显著目标结构之间的交互。为此，我们提出了SphereSOD，一个ERP原生框架，将全景几何与演化的显著结构耦合起来。具体而言，球面几何指导特征采样和空间加权，而粗粒度显著性和轮廓预测在渐进解码过程中影响上下文聚合。SphereSOD首先基于球面投影几何初始化可变形采样，然后采用有界、内容自适应的偏移，生成与底层全景几何更对齐的特征。随后，解码器执行结构引导的上下文聚合和渐进细化，以恢复完整的显著区域和精确的边界。在三个公开的360度SOD基准上的大量实验表明，该方法达到了最先进的性能，并实现了良好的精度-效率权衡，支持直接在ERP空间中进行保持结构的推理，作为投影密集型全景管线的一种有前景的替代方案。
英文摘要
360° salient object detection (SOD) aims to accurately segment salient regions across a full field of view. However, equirectangular projection (ERP) introduces severe spatial distortion when mapping the spherical domain onto a planar representation. Existing methods mainly focus on compensating projection distortion while overlooking the interaction between panoramic geometry and salient object structure during feature perception and prediction refinement. To this end, we propose SphereSOD, an ERP-native framework that couples panoramic geometry with evolving salient structures. Specifically, spherical geometry governs feature sampling and spatial weighting, while coarse-grained saliency and contour prediction influence context aggregation during the progressive decoding process. SphereSOD first initializes deformable sampling based on spherical projection geometry and then employs bounded, content-adaptive offsets, yielding features that are better aligned with the underlying panoramic geometry. Subsequently, the decoder performs structure-guided context aggregation and progressive refinement to recover complete salient regions and accurate boundaries. Extensive experiments on three public 360° SOD benchmarks demonstrate state-of-the-art performance and a favorable accuracy-efficiency trade-off, supporting structurepreserving inference directly in ERP space as a promising alternative to projection-heavy panoramic pipelines.
Comments12 pages
