OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3

TL;DR

OmniOVCD introduces a novel framework leveraging SAM 3's integrated segmentation and identification capabilities for open-vocabulary change detection, achieving state-of-the-art results without relying on multiple models.

Contribution

The paper proposes a standalone OVCD framework using SAM 3's decoupled output heads and a fusion strategy, improving accuracy and stability over existing methods.

Findings

Achieves state-of-the-art IoU scores on four benchmarks.

Effectively fuses semantic, instance, and presence outputs for accurate land-cover masks.

Maintains high category recognition accuracy and instance-level consistency.

Abstract

Change Detection (CD) is a fundamental task in remote sensing. It monitors the evolution of land cover over time. Based on this, Open-Vocabulary Change Detection (OVCD) introduces a new requirement. It aims to reduce the reliance on predefined categories. Existing training-free OVCD methods mostly use CLIP to identify categories. These methods also need extra models like DINO to extract features. However, combining different models often causes problems in matching features and makes the system unstable. Recently, the Segment Anything Model 3 (SAM 3) is introduced. It integrates segmentation and identification capabilities within one promptable model, which offers new possibilities for the OVCD task. In this paper, we propose OmniOVCD, a standalone framework designed for OVCD. By leveraging the decoupled output heads of SAM 3, we propose a Synergistic Fusion to Instance Decoupling (SFID) strategy. SFID first fuses the semantic, instance, and presence outputs of SAM 3 to construct land-cover masks, and then decomposes them into individual instance masks for change comparison. This design preserves high accuracy in category recognition and maintains instance-level consistency across images. As a result, the model can generate accurate change masks. Experiments on four public benchmarks (LEVIR-CD, WHU-CD, S2Looking, and SECOND) demonstrate SOTA performance, achieving IoU scores of 67.2, 66.5, 24.5, and 27.1 (class-average), respectively, surpassing all previous methods. The code is available at https://github.com/Erxucomeon/OmniOVCD.