PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion

Mahdi Chamseddine, Didier Stricker, Jason Rambach
1/12/2026
cs.CV

Official code: dfki-av/PanoSAMic (12 stars, last commit 2026-04-13).

Abstract

Existing image foundation models are not optimized for spherical images having been trained primarily on perspective images. PanoSAMic integrates the pre-trained Segment Anything (SAM) encoder to make use of its extensive training and integrate it into a semantic segmentation model for panoramic images using multiple modalities. We modify the SAM encoder to output multi-stage features and introduce a novel spatio-modal fusion module that allows the model to select the relevant modalities and best features from each modality for different areas of the input. Furthermore, our semantic decoder uses spherical attention and dual view fusion to overcome the distortions and edge discontinuity often associated with panoramic images. PanoSAMic achieves state-of-the-art (SotA) results on Stanford2D3DS for RGB, RGB-D, and RGB-D-N modalities and on Matterport3D for RGB and RGB-D modalities. https://github.com/dfki-av/PanoSAMic

View on arXivView PDF

Code Implementations(1)

dfki-av/PanoSAMicOfficial100%

[ICPR'26] PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion

122Shell, PythonDec 2, 20256 months agoNOASSERTION
modality-fusionsemantic-segmentationspherical-images

Similar Papers

REL-SF4PASS: Panoramic Semantic Segmentation with REL Depth Representation and Spherical Fusion

83% match2026

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

82% match1 repo402024

LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment

82% match1 repo922026

Scene-Centric Unsupervised Panoptic Segmentation

81% match1 repo942026

Multi-source Domain Adaptation for Panoramic Semantic Segmentation

81% match1 repo92024

EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation

81% match1 repo322026

Cite this paper

@article{chamseddine2026panosamic,
  title  = {PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion},
  author = {Mahdi Chamseddine and Didier Stricker and Jason Rambach},
  year   = {2026},
  eprint = {2601.07447},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.07447v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.07447.svg)](https://codeofpaper.com/paper/2601.07447)

Discussion