# CamSAM2: Segment Anything Accurately in Camouflaged Videos

arXiv: https://arxiv.org/abs/2503.19730 · HTML: https://mlsanity.com/paper/2503.19730/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 30 of 46)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [Anabranch Network for Camouflaged Object Segmentation](https://mlsanity.com/paper/2105.09451/) (2021)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Video Polyp Segmentation: A Deep Learning Perspective](https://mlsanity.com/paper/2203.14291/) (2022)
- [Progressively Normalized Self-Attention Network for Video Polyp Segmentation](https://mlsanity.com/paper/2105.08468/) (2021)
- [It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos](https://mlsanity.com/paper/1604.00136/) (2016)
- [SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation](https://mlsanity.com/paper/2408.08870/) (2024)
- [Segmenting Moving Objects via an Object-Centric Layered Representation](https://mlsanity.com/paper/2207.02206/) (2022)
- [Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation](https://mlsanity.com/paper/2011.11630/) (2020)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [CamoFormer: Masked Separable Attention for Camouflaged Object Detection](https://mlsanity.com/paper/2212.06570/) (2022)
- [Semi-Supervised Video Salient Object Detection Using Pseudo-Labels](https://mlsanity.com/paper/1908.04051/) (2019)
- [ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection](https://mlsanity.com/paper/2310.20208/) (2023)
- [Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning](https://mlsanity.com/paper/2408.07931/) (2024)
- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information](https://mlsanity.com/paper/2206.02846/) (2022)
- [SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection](https://mlsanity.com/paper/2408.10760/) (2024)

## Built on by (most cited first, 7 of 7)

- [StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios](https://mlsanity.com/paper/2512.04451/) (2025)
- [Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025](https://mlsanity.com/paper/2506.05856/) (2025)
- [Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environments](https://mlsanity.com/paper/2509.14012/) (2025)
- [LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation](https://mlsanity.com/paper/2510.25263/) (2025)
- [Live Interactive Training for Video Segmentation](https://mlsanity.com/paper/2603.26929/) (2026)
- [PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation](https://mlsanity.com/paper/2604.07901/) (2026)
- [CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild](https://mlsanity.com/paper/2604.08287/) (2026)

## Abstract (arXiv)

Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-world applications. With the release of SAM2, video segmentation has witnessed significant progress. However, SAM2's capability of segmenting camouflaged videos is suboptimal, especially when given simple prompts such as point and box. To address the problem, we propose Camouflaged SAM2 (CamSAM2), which enhances SAM2's ability to handle camouflaged scenes without modifying SAM2's parameters. Specifically, we introduce a decamouflaged token to provide the flexibility of feature adjustment for VCOS. To make full use of fine-grained and high-resolution features from the current frame and previous frames, we propose implicit object-aware fusion (IOF) and explicit object-aware fusion (EOF) modules, respectively. Object prototype generation (OPG) is introduced to abstract and memorize object prototypes with informative details using high-quality features from previous frames. Extensive experiments are conducted to validate the effectiveness of our approach. While CamSAM2 only adds negligible learnable parameters to SAM2, it substantially outperforms SAM2 on three VCOS datasets, especially achieving 12.2 mDice gains with click prompt on MoCA-Mask and 19.6 mDice gains with mask prompt on SUN-SEG-Hard, with Hiera-T as the backbone. The code is available at https://github.com/zhoustan/CamSAM2.