Amodal SAM: A Unified Amodal Segmentation Framework with Generalization

2026-04-22

AI Summary

This work addresses the challenges of predicting complete object geometry under occlusion and the limited generalization of existing methods by proposing a unified vision framework built upon the Segment Anything Model (SAM). The approach integrates a lightweight Spatial Completion Adapter, a Target-Aware Occlusion Synthesis strategy for realistic occlusion augmentation, and learning objectives that enforce region consistency and topological regularization. This enables effective amodal segmentation across both images and videos. The method achieves state-of-the-art performance on standard benchmarks and demonstrates significantly improved robustness and generalization to novel object categories and unseen scenarios.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these approaches often lack the generalization capacity to extend effectively to novel object categories and unseen contexts. This paper introduces Amodal SAM, a unified framework that leverages SAM (Segment Anything Model) for both amodal image and amodal video segmentation. Amodal SAM preserves the powerful generalization ability of SAM while extending its inherent capabilities to the amodal segmentation task. The improvements lie in three aspects: (1) a lightweight Spatial Completion Adapter that enables occluded region reconstruction, (2) a Target-Aware Occlusion Synthesis (TAOS) pipeline that addresses the scarcity of amodal annotations by generating diverse synthetic training data, and (3) novel learning objectives that enforce regional consistency and topological regularization. Extensive experiments demonstrate that Amodal SAM achieves state-of-the-art performance on standard benchmarks, while simultaneously exhibiting robust generalization to novel scenarios. We anticipate that this research will advance the field toward practical amodal segmentation systems capable of operating effectively in unconstrained real-world environments.

Problem

• amodal segmentation
• generalization
• occluded regions
• novel object categories
• unseen contexts

Innovation

• Amodal Segmentation
• Segment Anything Model (SAM)
• Spatial Completion Adapter
• Target-Aware Occlusion Synthesis
• Generalization