# Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics

arXiv: https://arxiv.org/abs/2604.24642 · HTML: https://mlsanity.com/paper/2604.24642/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Data Filtering Networks](https://mlsanity.com/paper/2309.17425/) (2023)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting](https://mlsanity.com/paper/2404.06903/) (2024)
- [Deep Sky Modeling for Single Image Outdoor Lighting Estimation](https://mlsanity.com/paper/1905.03897/) (2019)
- [LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation](https://mlsanity.com/paper/2408.13252/) (2024)
- [Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models](https://mlsanity.com/paper/2311.13141/) (2023)
- [Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models](https://mlsanity.com/paper/2310.18840/) (2023)
- [360-Degree Panorama Generation from Few Unregistered NFoV Images](https://mlsanity.com/paper/2308.14686/) (2023)
- [DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion](https://mlsanity.com/paper/2410.24203/) (2024)
- [CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation](https://mlsanity.com/paper/2501.17162/) (2025)
- [Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation](https://mlsanity.com/paper/2309.03467/) (2023)
- [FastScene: Text-Driven Fast 3D Indoor Scene Generation via Panoramic Gaussian Splatting](https://mlsanity.com/paper/2405.05768/) (2024)

## Abstract (arXiv)

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP) models, standard AI evaluators, predominantly trained on perspective image-text pairs, face an open question regarding their understanding of the unique characteristics of 360-degree panoramic image-text pairs. This paper addresses this gap by first introducing two concepts: 360-degree textual semantics, semantic information conveyed by explicit format identifiers, and 360-degree visual semantics, invariant semantics under horizontal circular shifts. To probe CLIP's comprehension of these semantics, we then propose novel evaluation methodologies using keyword manipulation and horizontal circular shifts of varying magnitudes. Rigorous statistical analyses across popular CLIP configurations reveal that: (1) CLIP models effectively leverage explicit textual identifiers, demonstrating an understanding of 360-degree textual semantics; and (2) CLIP models fail to robustly preserve semantic alignment under horizontal circular shifts, indicating limited comprehension of 360-degree visual semantics. To address this limitation, we propose a LoRA-based fine-tuning framework that explicitly instills invariance to circular shifts. Our fine-tuned models exhibit improved comprehension of 360-degree visual semantics, though with a slight degradation in original semantic evaluation performance, highlighting a fundamental trade-off in adapting CLIP to 360-degree panoramic images. Code is available at https://github.com/littlewhitesea/360Semantics.