# STORM: Segment, Track, and Object Re-Localization from a Single Image

arXiv: https://arxiv.org/abs/2511.09771 · HTML: https://mlsanity.com/paper/2511.09771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 64 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [CosyPose: Consistent multi-view multi-object 6D pose estimation](https://mlsanity.com/paper/2008.08465/) (2020)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [BOP: Benchmark for 6D Object Pose Estimation](https://mlsanity.com/paper/1808.08319/) (2018)
- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects](https://mlsanity.com/paper/1701.05498/) (2017)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [BOP Challenge 2020 on 6D Object Localization](https://mlsanity.com/paper/2009.07378/) (2020)
- [Siam R-CNN: Visual Tracking by Re-Detection](https://mlsanity.com/paper/1911.12836/) (2019)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation](https://mlsanity.com/paper/2311.15707/) (2023)
- [ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2203.09418/) (2022)
- [HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects](https://mlsanity.com/paper/1904.03167/) (2019)
- [Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention](https://mlsanity.com/paper/2505.17412/) (2025)
- [Segmentation-driven 6D Object Pose Estimation](https://mlsanity.com/paper/1812.02541/) (2018)
- [PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking](https://mlsanity.com/paper/1905.09304/) (2019)

## Abstract (arXiv)

Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD models, manual masking, or per-object adaptation, and still fail under occlusion or fast motion without a principled way to recognize failure. We propose STORM, a unified framework for reference-conditioned 6D tracking that can operate from a single reference image, with minimal manual input and improved robustness. STORM combines: (i) Hierarchical Spatial Fusion Attention (HSFA), a task-driven reference-query fusion architecture that supports both single-reference and multi-reference conditioning and can optionally use vision-language semantic conditioning to resolve instance ambiguities; and (ii) a BCE-trained tracking verifier whose continuous compatibility logit is used as an energy-like score to detect drift and trigger automatic re-initialization. Experiments on LM-O and YCB-Video show that STORM improves annotation-free pose tracking accuracy over strong baselines and recovers reliably from severe occlusions and rapid viewpoint changes with minimal overhead.