Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

• URL: http://arxiv.org/abs/2607.08765v2
• Date: Sun, 12 Jul 2026 11:09:35 GMT
• Title: Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
• Abstract summary: In this work, we present Canvas360, a two-stage framework for in-context panoramic generation.<n>We propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing.<n>On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization.
• Score: 20.15186580337447
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/

Related papers

• PanoWorld: Real-World Panoramic Generation [68.3569360188378]
  We propose PanoWorld, which simplifies camera trajectories into translations via fixed headings for both current-action modeling and long-range memory.<n>Extensive experiments on World360 demonstrate the effectiveness of PanoWorld, outperforming alternative methods by a large margin.
  arXiv  Detail & Related papers  (2026-07-10T17:59:32Z)
• World-Shaper: A Unified Framework for 360° Panoramic Editing [57.174341220144605]
  Existing perspective-based image editing methods fail to model the spatial structure of panoramas.<n>We present World-Shaper, a unified geometry-aware framework that bridges panoramic generation and editing within a single editing-centric design.<n>Our method achieves superior geometric consistency, editing fidelity, and text controllability compared to SOTA methods.
  arXiv  Detail & Related papers  (2026-01-30T19:38:54Z)
• AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding [58.90269958632018]
  Single-view indoor scene generation plays a crucial role in a range of real-world applications.<n>Recent approaches have made progress by leveraging diffusion models and depth estimation networks.<n>We propose AnchoredDream, a novel zero-shot pipeline that anchors 360 scene generation on high-fidelity geometry.
  arXiv  Detail & Related papers  (2026-01-23T08:08:12Z)
• JoPano: Unified Panorama Generation via Joint Modeling [51.392082596383034]
  We propose a joint-face panorama (JoPano) generation approach that unifies the two core tasks within a DiT-based model.<n>We show that JoPano can generate high-quality panoramas for both text-to-panorama and view-to-panorama generation tasks.
  arXiv  Detail & Related papers  (2025-12-07T15:19:26Z)
• DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training [76.82789568988557]
  DiT360 is a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation.<n>Our method achieves better boundary consistency and image fidelity across eleven quantitative metrics.
  arXiv  Detail & Related papers  (2025-10-13T17:59:15Z)
• TanDiT: Tangent-Plane Diffusion Transformer for High-Quality 360° Panorama Generation [12.480249699450535]
  TanDiT is a method that synthesizes panoramic scenes by generating grids of tangent-plane images covering the entire 360$circ$ view.<n>To accurately assess panoramic image quality, we also present two specialized metrics, TangentIS and TangentFID.
  arXiv  Detail & Related papers  (2025-06-26T18:09:09Z)
• PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms [41.92179513409301]
  Existing panoramic video generation models struggle to leverage pre-trained generative priors from conventional text-to-video models for high-quality panoramic videos.<n>In this paper, we introduce PanoWan to effectively lift pre-trained text-to-video models to the panoramic domain, equipped with minimal modules.<n>To provide sufficient panoramic videos for learning these lifted representations, we contribute PanoVid, a high-quality panoramic video dataset with captions and diverse scenarios.
  arXiv  Detail & Related papers  (2025-05-28T06:24:21Z)
• DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion [60.45000652592418]
  We propose a novel text-driven panoramic generation framework, DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. We show that DiffPano can generate consistent, diverse panoramic images with given unseen text descriptions and camera poses.
  arXiv  Detail & Related papers  (2024-10-31T17:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.