# SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generation

arXiv: https://arxiv.org/abs/2606.12213 · HTML: https://mlsanity.com/paper/2606.12213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 31)

- [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)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [Round and Round We Go! What makes Rotary Positional Encodings useful?](https://mlsanity.com/paper/2410.06205/) (2024)
- [SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions](https://mlsanity.com/paper/2306.05178/) (2023)
- [HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels](https://mlsanity.com/paper/2507.21809/) (2025)
- [PanoDiffusion: 360-degree Panorama Outpainting via Diffusion](https://mlsanity.com/paper/2307.03177/) (2023)
- [Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models](https://mlsanity.com/paper/2311.13141/) (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)
- [One Flight Over the Gap: A Survey from Perspective to Panoramic Vision](https://mlsanity.com/paper/2509.04444/) (2025)
- [DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training](https://mlsanity.com/paper/2510.11712/) (2025)
- [PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanisms](https://mlsanity.com/paper/2505.22016/) (2025)
- [SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model](https://mlsanity.com/paper/2403.10044/) (2024)
- [What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?](https://mlsanity.com/paper/2505.22129/) (2025)
- [Panorama Generation From NFoV Image Done Right](https://mlsanity.com/paper/2503.18420/) (2025)
- [Geometry Fidelity for Spherical Images](https://mlsanity.com/paper/2407.18207/) (2024)
- [Conditional Panoramic Image Generation via Masked Autoregressive Modeling](https://mlsanity.com/paper/2505.16862/) (2025)
- [360Anything: Geometry-Free Lifting of Images and Videos to 360deg](https://mlsanity.com/paper/2601.16192/) (2026)

## Abstract (arXiv)

Panoramic imagery is increasingly used in world-generation, games, and simulation, where users may need not only photorealistic scenes but also stylized and non-photorealistic environments. Large-scale text-to-image diffusion and flow models provide broad style and semantic priors for this goal, but planar image training misaligns them with the wrap-around topology and polar regions of 360^circ panoramas represented in equirectangular projection (ERP). We present SHERPA, a lightweight adaptation framework that combines frequency-selective Circular RoPE, Circular Latent Encoding/Decoding, image-side FFN adapters, and a Dual-Path Training Scheme. Circular RoPE replaces only the seam-sensitive high-frequency horizontal RoPE band with integer-periodic harmonics while preserving the pretrained lower-frequency spectrum. The Paired Panorama Path supervises geometry, while the Unpaired Style Path uses self-supervised yaw consistency for target-free stylized prompts. As a result, SHERPA generates 360^circ panoramas across both photorealistic panorama domains and open-domain stylized prompts.