# DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

arXiv: https://arxiv.org/abs/2510.11712 · HTML: https://mlsanity.com/paper/2510.11712/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 77 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 30 of 64)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [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)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion](https://mlsanity.com/paper/2307.01097/) (2023)
- [SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions](https://mlsanity.com/paper/2306.05178/) (2023)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)

## Built on by (most cited first, 24 of 24)

- [HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds](https://mlsanity.com/paper/2604.14268/) (2026)
- [Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation](https://mlsanity.com/paper/2512.16913/) (2025)
- [AirSim360: A Panoramic Simulation Platform within Drone View](https://mlsanity.com/paper/2512.02009/) (2025)
- [CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation](https://mlsanity.com/paper/2602.06959/) (2026)
- [MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors](https://mlsanity.com/paper/2602.05330/) (2026)
- [PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World](https://mlsanity.com/paper/2605.13169/) (2026)
- [Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning](https://mlsanity.com/paper/2602.05321/) (2026)
- [MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data](https://mlsanity.com/paper/2603.25319/) (2026)
- [MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold](https://mlsanity.com/paper/2606.13376/) (2026)
- [Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models](https://mlsanity.com/paper/2604.10578/) (2026)
- [Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image](https://mlsanity.com/paper/2603.05908/) (2026)
- [Fly360: Omnidirectional Obstacle Avoidance within Drone View](https://mlsanity.com/paper/2603.06573/) (2026)
- [UniSHARP: Universal Sharp Monocular View Synthesis](https://mlsanity.com/paper/2606.07514/) (2026)
- [SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE](https://mlsanity.com/paper/2606.32033/) (2026)
- [Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator](https://mlsanity.com/paper/2607.05765/) (2026)
- [ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space](https://mlsanity.com/paper/2607.11673/) (2026)
- [Pano360: Perspective to Panoramic Vision with Geometric Consistency](https://mlsanity.com/paper/2603.12013/) (2026)
- [Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion](https://mlsanity.com/paper/2603.23179/) (2026)
- [Beyond Thinking: Imagining in 360^circ for Humanoid Visual Search](https://mlsanity.com/paper/2605.09146/) (2026)
- [LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR](https://mlsanity.com/paper/2605.11115/) (2026)
- [PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting](https://mlsanity.com/paper/2605.14135/) (2026)
- [SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generation](https://mlsanity.com/paper/2606.12213/) (2026)
- [Enhancing In-context Panoramic Generation via Geometric-aware Pretraining](https://mlsanity.com/paper/2607.08765/) (2026)
- [Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction](https://mlsanity.com/paper/2607.08769/) (2026)

## Abstract (arXiv)

In this work, we propose DiT360, a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation. For the issues of maintaining geometric fidelity and photorealism in generation quality, we attribute the main reason to the lack of large-scale, high-quality, real-world panoramic data, where such a data-centric view differs from prior methods that focus on model design. Basically, DiT360 has several key modules for inter-domain transformation and intra-domain augmentation, applied at both the pre-VAE image level and the post-VAE token level. At the image level, we incorporate cross-domain knowledge through perspective image guidance and panoramic refinement, which enhance perceptual quality while regularizing diversity and photorealism. At the token level, hybrid supervision is applied across multiple modules, which include circular padding for boundary continuity, yaw loss for rotational robustness, and cube loss for distortion awareness. Extensive experiments on text-to-panorama, inpainting, and outpainting tasks demonstrate that our method achieves better boundary consistency and image fidelity across eleven quantitative metrics. Our code is available at https://github.com/Insta360-Research-Team/DiT360.