paper-with-me

홈 › Papers

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

2026-06-10 · Jungwoon Kang, Jaehun Kim, Yiwon Yu, Hyungyum Jang, Sanghoon Lee, Jongyoo Kim 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.

📄 PDF Abstract BibTeX arXiv:2606.12213

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sherpa: Robust Hyperparameter Optimization for Machine Learning

2020-05-08 · Lars Hertel, Julian Collado, Peter Sadowski, Jordan Ott 외

Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of d…

BIG-bench Machine LearningHyperparameter Optimization

Sherpa: a Mission-Independent Data Analysis Application

2001-08-27 · Peter E. Freeman, Stephen Doe, Aneta Siemiginowska

The ever-increasing quality and complexity of astronomical data underscores the need for new and powerful data analysis applications. This need has led to the development of Sherpa, a modeling and fitting program in the …

parameter estimation

Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation

2023-10-31 · Jinwei Zhang, Lianrui Zuo, Blake E. Dewey, Samuel W. Remedios 외

Deep learning algorithms utilizing magnetic resonance (MR) images have demonstrated cutting-edge proficiency in autonomously segmenting multiple sclerosis (MS) lesions. Despite their achievements, these algorithms may st…

Domain AdaptationDomain GeneralizationLesion Segmentation

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

2023-12-11 · CVPR 2024 1 · Fangfu Liu, Diankun Wu, Yi Wei, Yongming Rao 외

Recently, 3D content creation from text prompts has demonstrated remarkable progress by utilizing 2D and 3D diffusion models. While 3D diffusion models ensure great multi-view consistency, their ability to generate high-…

3D GenerationText to 3D

HarmonPaint: Harmonized Training-Free Diffusion Inpainting

2025-07-22 · Ying Li, Xinzhe Li, Yong Du, Yangyang Xu 외 arxiv

Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the sur…

Image Inpainting