360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation
Hai Wang, Jing-Hao Xue

TL;DR
360PanT is a training-free method for translating 360-degree panoramas with preserved boundary continuity, using boundary encoding and spatial control to ensure seamless, immersive results without boundary artifacts.
Contribution
It introduces a novel training-free approach that encodes boundary information and enables seamless, boundary-preserving panorama translation guided by text prompts.
Findings
Achieves seamless boundary continuity in panorama translation
Effective on real-world and synthesized datasets
Outperforms existing methods in boundary preservation
Abstract
Preserving boundary continuity in the translation of 360-degree panoramas remains a significant challenge for existing text-driven image-to-image translation methods. These methods often produce visually jarring discontinuities at the translated panorama's boundaries, disrupting the immersive experience. To address this issue, we propose 360PanT, a training-free approach to text-based 360-degree panorama-to-panorama translation with boundary continuity. Our 360PanT achieves seamless translations through two key components: boundary continuity encoding and seamless tiling translation with spatial control. Firstly, the boundary continuity encoding embeds critical boundary continuity information of the input 360-degree panorama into the noisy latent representation by constructing an extended input image. Secondly, leveraging this embedded noisy latent representation and guided by a target…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Video Analysis and Summarization · Multimodal Machine Learning Applications
