paper-with-me

홈 › Papers

SAP: Segment Any 4K Panorama

2026-03-13 · Lutao Jiang, Zidong Cao, Weikai Chen, Xu Zheng, Yuanhuiyi Lyu, Zhenyang Li, Zeyu HU, Yingda Yin, Keyang Luo, Runze Zhang, Kai Yan, Shengju Qian, Haidi Fan, Yifan Peng, Xin Wang, Hui Xiong, Ying-Cong Chen arxiv

Promptable instance segmentation is widely adopted in embodied and AR systems, yet the performance of foundation models trained on perspective imagery often degrades on 360° panoramas. In this paper, we introduce Segment Any 4K Panorama (SAP), a foundation model for 4K high-resolution panoramic instance-level segmentation. We reformulate panoramic segmentation as fixed-trajectory perspective video segmentation, decomposing a panorama into overlapping perspective patches sampled along a continuous spherical traversal. This memory-aligned reformulation preserves native 4K resolution while restoring the smooth viewpoint transitions required for stable cross-view propagation. To enable large-scale supervision, we synthesize 183,440 4K-resolution panoramic images with instance segmentation labels using the InfiniGen engine. Trained under this trajectory-aligned paradigm, SAP generalizes effectively to real-world 360° images, achieving +17.2 zero-shot mIoU gain over vanilla SAM2 of different sizes on real-world 4K panorama benchmark.

📄 PDF Abstract BibTeX arXiv:2603.12759

Code (0)

등록된 구현이 없습니다.

Tasks

Instance SegmentationVideo Segmentation

Similar Papers 제목 키워드 기반

Cross-View Panorama Image Synthesis

2022-03-22 · Songsong Wu, Hao Tang, Xiao-Yuan Jing, Haifeng Zhao 외

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different v…

Image Generation

PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation

2022-03-17 · Zhijie Shen, Chunyu Lin, Kang Liao, Lang Nie 외

Existing panoramic depth estimation methods based on convolutional neural networks (CNNs) focus on removing panoramic distortions, failing to perceive panoramic structures efficiently due to the fixed receptive field in …

Depth EstimationSemantic Segmentation

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

2026-09-16 · Sara Pieri, Evangelos Kazakos, Shizhe Chen, Josef Sivic 외 hf

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image captions, but reliably…

Panoptic SegmentationDense CaptioningPhrase Grounding

PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms

2026-03-20 · Tuna Gürbüz, Ege Özsoy, Tony Danjun Wang, Nassir Navab arxiv

Operating rooms (ORs) are cluttered, dynamic, highly occluded environments, where reliable spatial understanding is essential for situational awareness during complex surgical workflows. Achieving spatial understanding f…

Panoptic Segmentation

SE360: Semantic Edit in 360$^\circ$ Panoramas via Hierarchical Data Construction

2025-12-23 · Haoyi Zhong, Fang-Lue Zhang, Andrew Chalmers, Taehyun Rhee arxiv

While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and …

Image Editing