# MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep Thinking

arXiv: https://arxiv.org/abs/2504.06863 · HTML: https://mlsanity.com/paper/2504.06863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding](https://mlsanity.com/paper/2310.15308/) (2023)
- [SwiftNet: Real-time Video Object Segmentation](https://mlsanity.com/paper/2102.04604/) (2021)
- [Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.03138/) (2022)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier](https://mlsanity.com/paper/2112.12402/) (2021)
- [D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos](https://mlsanity.com/paper/2111.07774/) (2021)
- [Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models](https://mlsanity.com/paper/2311.17095/) (2023)

## Abstract (arXiv)

Moving object segmentation plays a vital role in understanding dynamic visual environments. While existing methods rely on multi-frame image sequences to identify moving objects, single-image MOS is critical for applications like motion intention prediction and handling camera frame drops. However, segmenting moving objects from a single image remains challenging for existing methods due to the absence of temporal cues. To address this gap, we propose MovSAM, the first framework for single-image moving object segmentation. MovSAM leverages a Multimodal Large Language Model (MLLM) enhanced with Chain-of-Thought (CoT) prompting to search the moving object and generate text prompts based on deep thinking for segmentation. These prompts are cross-fused with visual features from the Segment Anything Model (SAM) and a Vision-Language Model (VLM), enabling logic-driven moving object segmentation. The segmentation results then undergo a deep thinking refinement loop, allowing MovSAM to iteratively improve its understanding of the scene context and inter-object relationships with logical reasoning. This innovative approach enables MovSAM to segment moving objects in single images by considering scene understanding. We implement MovSAM in the real world to validate its practical application and effectiveness for autonomous driving scenarios where the multi-frame methods fail. Furthermore, despite the inherent advantage of multi-frame methods in utilizing temporal information, MovSAM achieves state-of-the-art performance across public MOS benchmarks, reaching 92.5% on J&F. Our implementation will be available at https://github.com/IRMVLab/MovSAM.