NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gandyra, Max, Santonicola, Alessandro, Beetz, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917116873015296
author Gandyra, Max
Santonicola, Alessandro
Beetz, Michael
author_facet Gandyra, Max
Santonicola, Alessandro
Beetz, Michael
contents Instance segmentation of novel objects instances in RGB images, given some example images for each object, is a well known problem in computer vision. Designing a model general enough to be employed for all kinds of novel objects without (re-) training has proven to be a difficult task. To handle this, we present a new training-free framework, called: Novel Object Cyclic Threshold based Instance Segmentation (NOCTIS). NOCTIS integrates two pre-trained models: Grounded-SAM 2 for object proposals with precise bounding boxes and corresponding segmentation masks; and DINOv2 for robust class and patch embeddings, due to its zero-shot capabilities. Internally, the proposal-object matching is realized by determining an object matching score based on the similarity of the class embeddings and the average maximum similarity of the patch embeddings with a new cyclic thresholding (CT) mechanism that mitigates unstable matches caused by repetitive textures or visually similar patterns. Beyond CT, NOCTIS introduces: (i) an appearance score that is unaffected by object selection bias; (ii) the usage of the average confidence of the proposals' bounding box and mask as a scoring component; and (iii) an RGB-only pipeline that performs even better than RGB-D ones. We empirically show that NOCTIS, without further training/fine tuning, outperforms the best RGB and RGB-D methods regarding the mean AP score on the seven core datasets of the BOP 2023 challenge for the "Model-based 2D segmentation of unseen objects" task.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01463
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
Gandyra, Max
Santonicola, Alessandro
Beetz, Michael
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2; I.4; I.5
Instance segmentation of novel objects instances in RGB images, given some example images for each object, is a well known problem in computer vision. Designing a model general enough to be employed for all kinds of novel objects without (re-) training has proven to be a difficult task. To handle this, we present a new training-free framework, called: Novel Object Cyclic Threshold based Instance Segmentation (NOCTIS). NOCTIS integrates two pre-trained models: Grounded-SAM 2 for object proposals with precise bounding boxes and corresponding segmentation masks; and DINOv2 for robust class and patch embeddings, due to its zero-shot capabilities. Internally, the proposal-object matching is realized by determining an object matching score based on the similarity of the class embeddings and the average maximum similarity of the patch embeddings with a new cyclic thresholding (CT) mechanism that mitigates unstable matches caused by repetitive textures or visually similar patterns. Beyond CT, NOCTIS introduces: (i) an appearance score that is unaffected by object selection bias; (ii) the usage of the average confidence of the proposals' bounding box and mask as a scoring component; and (iii) an RGB-only pipeline that performs even better than RGB-D ones. We empirically show that NOCTIS, without further training/fine tuning, outperforms the best RGB and RGB-D methods regarding the mean AP score on the seven core datasets of the BOP 2023 challenge for the "Model-based 2D segmentation of unseen objects" task.
title NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2; I.4; I.5
url https://arxiv.org/abs/2507.01463