寻求分割：全景指代分割的主动感知
Seek to Segment: Active Perception for Panoramic Referring Segmentation
AI总结：
提出主动全景指代分割任务，通过记忆增强智能体PanoSeeker结合视觉语言模型与空间记忆，实现高效搜索与分割。
摘要：
现有的指代分割模型被动处理固定视角的静态图像，限制了它们在具身AI中的应用，其中智能体必须在连续的360$^\circ$环境中进行主动感知。为弥补这一差距，我们引入了一项新任务：主动全景指代分割（APRS）。在此设置中，智能体需要调整其视角（$\Delta\theta, \Delta\phi$）以探索360$^\circ$环境，寻找用户指令指定的对象进行分割。为应对这一挑战，我们提出了PanoSeeker，一种用于高效APRS的记忆增强智能体。PanoSeeker不依赖启发式扫描，而是将视觉语言模型（VLM）与EgoSphere（一种显式空间视觉记忆）相结合。通过将顺序局部观测逐步整合为统一的360$^\circ$表示，EgoSphere使智能体能够规划高效且无冗余的搜索轨迹。一旦找到目标，智能体执行主动视角对齐并输出分割掩码。此外，我们整理了一个带有记忆时间线的专家标注搜索轨迹数据集用于监督微调，随后进行强化学习后训练以显式优化PanoSeeker的探索效率。在我们新建立的APRS基准上的大量实验表明，PanoSeeker实现了卓越的搜索效率和分割精度，显著优于改编的最先进基线。
英文摘要：
Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform active perception in the continuous 360$^\circ$ environments. To bridge this gap, we introduce a novel task: Active Panoramic Referring Segmentation (APRS). In this setting, an agent is required to adjust its viewing direction ($Δθ, Δϕ$) to explore the 360$^\circ$ environment, seeking the object specified by a user instruction for segmentation. To tackle this challenging task, we propose PanoSeeker, a memory-augmented agent for efficient APRS. Rather than relying on heuristic scanning, PanoSeeker integrates a Vision-Language Model (VLM) with EgoSphere, an explicit spatial visual memory. By progressively integrating sequential local observations into a unified 360$^\circ$ representation, EgoSphere enables the agent to plan efficient and non-redundant search trajectories. Once the target is found, the agent performs active viewpoint alignment and outputs the segmentation mask. Furthermore, we curate an expert-annotated search trajectory dataset with memory timelines for Supervised Fine-Tuning, followed by Reinforcement Learning post-training to explicitly optimize PanoSeeker's exploration efficiency. Extensive experiments on our newly established APRS benchmark demonstrate that PanoSeeker achieves superior search efficiency and segmentation accuracy, significantly outperforming adapted state-of-the-art baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
