# DynEoMT: Learning Object Dynamicity from Online Segmentation Queries

arXiv: https://arxiv.org/abs/2609.14466 · HTML: https://mlsanity.com/paper/2609.14466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Video Panoptic Segmentation](https://mlsanity.com/paper/2006.11339/) (2020)
- [DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes](https://mlsanity.com/paper/1806.05620/) (2018)
- [MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training](https://mlsanity.com/paper/2208.02245/) (2022)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [STEP: Segmenting and Tracking Every Pixel](https://mlsanity.com/paper/2102.11859/) (2021)
- [Your ViT is Secretly an Image Segmentation Model](https://mlsanity.com/paper/2503.19108/) (2025)
- [MemFlow: Optical Flow Estimation and Prediction with Memory](https://mlsanity.com/paper/2404.04808/) (2024)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [DVIS++: Improved Decoupled Framework for Universal Video Segmentation](https://mlsanity.com/paper/2312.13305/) (2023)
- [Segment Any Motion in Videos](https://mlsanity.com/paper/2503.22268/) (2025)
- [Moving Object Segmentation: All You Need Is SAM (and Flow)](https://mlsanity.com/paper/2404.12389/) (2024)
- [EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation](https://mlsanity.com/paper/2011.08332/) (2020)
- [DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries](https://mlsanity.com/paper/2404.00086/) (2024)
- [RoMo: Robust Motion Segmentation Improves Structure from Motion](https://mlsanity.com/paper/2411.18650/) (2024)
- [Learning segmentation from point trajectories](https://mlsanity.com/paper/2501.12392/) (2025)
- [InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation](https://mlsanity.com/paper/2301.01882/) (2023)
- [VidEoMT: Your ViT is Secretly Also a Video Segmentation Model](https://mlsanity.com/paper/2602.17807/) (2026)
- [Is Semantic SLAM Ready for Embedded Systems ? A Comparative Survey](https://mlsanity.com/paper/2505.12384/) (2025)
- [GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry](https://mlsanity.com/paper/2602.21810/) (2026)
- [GMOS: Grounding Moving Object Segmentation in 3D Space and Time](https://mlsanity.com/paper/2605.30352/) (2026)

## Abstract (arXiv)

Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity attribute cannot be inferred from semantics alone and is confounded by camera ego-motion. We introduce method, an online framework that augments query-based video segmentation with region-level dynamicity prediction. It jointly produces the original segmentation outputs and a dynamic or static state for each predicted region. At inference, DynEoMT uses only the current frame and propagated queries, without optical flow, depth, camera pose, previous RGB frames, or feature maps. Because established video segmentation benchmarks do not annotate this attribute, we also introduce a class-agnostic offline supervision pipeline using camera-compensated optical flow and confidence-aware temporal filtering. Across VIPSeg, OVIS, YouTube-VIS 2022, and VSPW, DynEoMT achieves balanced accuracies of 84.3, 68.0, 68.6, and 87.6, respectively, while largely preserving segmentation performance. These results show that segmentation-region dynamicity can be learned from propagated queries, enabling its online prediction without a dedicated motion-processing pipeline at inference. The complete code will be released as open source to enable full reproduction of the method and experiments.