Research map / Detection and segmentation / Open-set and few-shot detection
OpenPanoD: Aligning Multimodal Prompts and Spherical Representations for Open-Vocabulary Panoramic Detection
Hang Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add visual prompts to text prompts (ablation) | OpenPanoD (planar ERP) · PANDORA | mAP novel: 24.9 -> 26.1 | Improved |
| add supervised contrastive loss (ablation) | OpenPanoD (planar ERP) · PANDORA | mAP novel: 26.1 -> 29.6 | Improved |
| replace planar ERP encoder with GeoFormer (ablation) | OpenPanoD · PANDORA | mAP novel: 29.6 -> 31.3 | Improved |
| replace ViT encoder with GeoFormer (ablation) | OpenPanoD · PANDORA | mAP novel: 29.6 -> 31.3 (+1.7) | Improved |
| replace SphereUFormer with GeoFormer (ablation) | OpenPanoD · PANDORA | mAP novel: 30.2 -> 31.3 (+1.1) | Improved |
| increase text prompts from 1 to 10 (ablation) | OpenPanoD · 360-Indoor | mAP: 24.6 -> 26.4 | Improved |
| increase text prompts from 10 to 20 (ablation) | OpenPanoD · 360-Indoor | mAP: 26.4 -> 26.3 | No clear effect |
| increase image prompts from 5 to 20 (ablation) | OpenPanoD · 360-Indoor | mAP: 25.5 -> 24.7 | Hurt |
| increase image prompts from 5 to 20 (ablation) | OpenPanoD · PANDORA | mAP: 23.3 -> 22.3 | Hurt |
| use multimodal rather than text-only prompts | OpenPanoD · 360-Indoor | mAP novel: 29.8 -> 33.9 | Improved |
| OpenPanoD vs Prompt-DINO (strongest baseline) | OpenPanoD multimodal · 360-Indoor | mAP novel: 26.8 -> 33.9 (+7.1) | Improved |
| OpenPanoD vs Prompt-DINO (strongest baseline) | OpenPanoD multimodal · PANDORA | mAP novel: 25.5 -> 31.3 (+5.8) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- T-Rex2 — T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Open Panoramic Segmentation (ECCV 2024 · similarity 0.89)
- More than the Sum: Panorama-Language Models for Adverse Omni-Scenes (CVPR 2026 · similarity 0.87)
- PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World (NeurIPS 2026 · similarity 0.87)
- Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection (AAAI 2025 · similarity 0.86)
- OpenView: Empowering MLLMs with Out-of-view VQA (NeurIPS 2026 · similarity 0.85)
- AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
