Details
| Original language | English |
|---|---|
| Pages (from-to) | 72456-72476 |
| Number of pages | 21 |
| Journal | IEEE ACCESS |
| Volume | 13 |
| Publication status | Published - 15 Apr 2025 |
Abstract
Panoramic images offer a comprehensive spatial view that is crucial for indoor robotics tasks such as visual room rearrangement, where an agent must restore objects to their original positions or states. Unlike existing 2D scene change understanding datasets, which rely on single-view images, panoramic views capture richer spatial context, object relationships, and occlusions—making them better suited for embodied artificial intelligence (AI) applications. To address this, we introduce Panoramic Scene Change Understanding (PanoSCU), a dataset specifically designed to enhance the visual object rearrangement task. Our dataset comprises 5,300 panoramas generated in an embodied simulator, encompassing 48 common indoor object classes. PanoSCU supports eight research tasks: single-view and panoramic detection, single-view and panoramic segmentation, single-view and panoramic change understanding, embodied object tracking, and change reversal. We also present PanoStitch, a training-free method for automatic panoramic data collection within embodied environments. We evaluate state-of-the-art methods on panoramic segmentation and change understanding tasks. There is a gap in existing methods, as they are not designed for panoramic inputs and struggle with varying ratios and sizes, resulting from the unique challenges of visual object rearrangement. Our findings reveal these limitations and underscore PanoSCU’s potential to drive progress in developing models capable of robust panoramic reasoning and fine-grained scene change understanding.
Keywords
- change detection algorithms, embodied artificial intelligence, image stitching, Object segmentation
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
- Materials Science(all)
- General Materials Science
- Engineering(all)
- General Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE ACCESS, Vol. 13, 15.04.2025, p. 72456-72476.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - PanoSCU
T2 - A Simulation-Based Dataset for Panoramic Indoor Scene Understanding
AU - Khan, Mariia
AU - Qiu, Yue
AU - Cong, Yuren
AU - Abu-Khalaf, Jumana
AU - Suter, David
AU - Rosenhahn, Bodo
N1 - Publisher Copyright: © 2013 IEEE.
PY - 2025/4/15
Y1 - 2025/4/15
N2 - Panoramic images offer a comprehensive spatial view that is crucial for indoor robotics tasks such as visual room rearrangement, where an agent must restore objects to their original positions or states. Unlike existing 2D scene change understanding datasets, which rely on single-view images, panoramic views capture richer spatial context, object relationships, and occlusions—making them better suited for embodied artificial intelligence (AI) applications. To address this, we introduce Panoramic Scene Change Understanding (PanoSCU), a dataset specifically designed to enhance the visual object rearrangement task. Our dataset comprises 5,300 panoramas generated in an embodied simulator, encompassing 48 common indoor object classes. PanoSCU supports eight research tasks: single-view and panoramic detection, single-view and panoramic segmentation, single-view and panoramic change understanding, embodied object tracking, and change reversal. We also present PanoStitch, a training-free method for automatic panoramic data collection within embodied environments. We evaluate state-of-the-art methods on panoramic segmentation and change understanding tasks. There is a gap in existing methods, as they are not designed for panoramic inputs and struggle with varying ratios and sizes, resulting from the unique challenges of visual object rearrangement. Our findings reveal these limitations and underscore PanoSCU’s potential to drive progress in developing models capable of robust panoramic reasoning and fine-grained scene change understanding.
AB - Panoramic images offer a comprehensive spatial view that is crucial for indoor robotics tasks such as visual room rearrangement, where an agent must restore objects to their original positions or states. Unlike existing 2D scene change understanding datasets, which rely on single-view images, panoramic views capture richer spatial context, object relationships, and occlusions—making them better suited for embodied artificial intelligence (AI) applications. To address this, we introduce Panoramic Scene Change Understanding (PanoSCU), a dataset specifically designed to enhance the visual object rearrangement task. Our dataset comprises 5,300 panoramas generated in an embodied simulator, encompassing 48 common indoor object classes. PanoSCU supports eight research tasks: single-view and panoramic detection, single-view and panoramic segmentation, single-view and panoramic change understanding, embodied object tracking, and change reversal. We also present PanoStitch, a training-free method for automatic panoramic data collection within embodied environments. We evaluate state-of-the-art methods on panoramic segmentation and change understanding tasks. There is a gap in existing methods, as they are not designed for panoramic inputs and struggle with varying ratios and sizes, resulting from the unique challenges of visual object rearrangement. Our findings reveal these limitations and underscore PanoSCU’s potential to drive progress in developing models capable of robust panoramic reasoning and fine-grained scene change understanding.
KW - change detection algorithms
KW - embodied artificial intelligence
KW - image stitching
KW - Object segmentation
UR - http://www.scopus.com/inward/record.url?scp=105002779883&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2025.3561055
DO - 10.1109/ACCESS.2025.3561055
M3 - Article
AN - SCOPUS:105002779883
VL - 13
SP - 72456
EP - 72476
JO - IEEE ACCESS
JF - IEEE ACCESS
SN - 2169-3536
ER -