mlsanityData to 7 Oct 2026

From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes

arXiv 2603.03577 ↗First posted 3 Mar 2026cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered, previously unseen scene. Existing proposal-based approaches are highly sensitive to proposal quality and often fail under occlusion and background clutter. We propose L2G-Det, a local-to-global instance detection framework that bypasses explicit object proposals by leveraging dense patch-level matching between templates and the query image. Locally matched patches generate candidate points, which are refined through a candidate selection module to suppress false positives. The filtered points are then used to prompt an augmented Segment Anything Model (SAM) with instance-specific object tokens, enabling reliable reconstruction of complete instance masks. Experiments demonstrate improved performance over proposal-based methods in challenging open-world settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

35 of 47 references.

References · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2023Segment Anythingcited by 8,158
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  11. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  12. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
23 more
  1. 2016Learning without Forgettingcited by 2,465
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  3. 2022Visual Prompt Tuningcited by 1,674
  4. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2019Objects as Pointscited by 1,172
  7. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  9. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  10. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  11. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  12. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  13. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  14. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  15. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  16. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 86
  17. 2020OS2D: One-Stage One-Shot Object Detection by Matching Anchor Featurescited by 35
  18. 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
  19. 2018Target Driven Instance Detectioncited by 14
  20. 2023VoxDet: Voxel Learning for Novel Instance Detectioncited by 8
  21. 2025Solving Instance Detection from an Open-World Perspectivecited by 6
  22. 2024TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Taskscited by 5
  23. 2023A High-Resolution Dataset for Instance Detection with Multi-View Instance Capturecited by 4

Built on by

Not cited yet.