Abstract
Amodal segmentation aims to recover complete object shapes, including occluded regions with no visual appearance, whereas conventional segmentation focuses solely on visible areas. Existing methods typically rely on strong prompts, such as visible masks or bounding boxes, which are costly or impractical to obtain in real-world settings. While recent approaches such as the Segment Anything Model (SAM) support point-based prompts for guidance, they often perform direct mask regression without explicitly modeling shape evolution, limiting generalization in complex occlusion scenarios. Moreover, most existing methods suffer from a black-box nature, lacking geometric interpretability and offering limited insight into how occluded shapes are inferred. To deal with these limitations, we propose VELA, an end-to-end VElocity-driven Level-set Amodal segmentation method that performs explicit contour evolution from point-based prompts. VELA first constructs an initial level set function from image features and the point input, which then progressively evolves into the final amodal mask under the guidance of a shape-specific motion field predicted by a fully differentiable network. This network learns to generate evolution dynamics at each step, enabling geometrically grounded and topologically flexible contour modeling. Extensive experiments on COCOA-cls, D2SA, and KINS benchmarks demonstrate that VELA outperforms existing strongly prompted methods while requiring only a single-point prompt, validating the effectiveness of interpretable geometric modeling under weak guidance. The code will be publicly released.
Abstract (translated)
模态分割（amodal segmentation）的目标是恢复物体的完整形状，包括那些被遮挡且没有视觉外观的部分，而传统的分割方法仅关注可视区域。现有的方法通常依赖于强有力的提示，例如可见的掩码或边界框，在实际应用中获取这些提示的成本高昂或不切实际。尽管最近的一些方法，如“Segment Anything Model”（SAM），支持基于点的提示以提供指导，但它们常常直接进行掩码回归，并未显式地建模形状演变过程，这在处理复杂的遮挡场景时限制了其泛化能力。此外，大多数现有的方法具有黑箱特性，缺乏几何解释性，并且对如何推断被遮挡形状提供的见解有限。 为了克服这些局限性，我们提出了VELA（VElocity-driven Level-set Amodal segmentation），这是一种基于速度驱动的层级集模态分割方法，它从点提示出发进行显式的轮廓演变。VELA首先根据图像特征和输入点构建初始层次集合函数，然后在形状特定运动场预测网络提供的指导下逐步演变为最终的全形态掩码。该网络通过端到端学习生成每个步骤的演化动态，这使得基于几何原理的、拓扑灵活的轮廓建模成为可能。 在COCOA-cls、D2SA和KINS等基准测试中的大量实验表明，VELA在仅使用单点提示的情况下优于现有的强提示方法，验证了在弱指导下可解释的几何模型的有效性。该代码将公开发布。
URL
https://arxiv.org/abs/2508.01661
