{"ID":5443911,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-07T01:54:07.268702664Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.32033","arxiv_id":"2606.32033","title":"SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE","abstract":"We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization, or leverage multi-step optimization that incurs prohibitive inference latency. We observe that contemporary generative models natively exhibit some panoramic priors from large-scale training. However, these emergent capabilities are insufficient, as the models fundamentally fail to satisfy the rigorous topological constraints imposed by equirectangular projection (ERP). We introduce a zero-shot and optimization-free approach that resolves these constraints at inference time. Spherical RoPE replaces standard rotary position embeddings: low-frequency channels are re-parameterized as 3D Cartesian coordinates to natively encode the spherical manifold, while high-frequency channels are harmonically quantized to enforce exact periodicity. Coupled with complementary Semantic Distortion classifier-free guidance (CFG) that explicitly steers geometry, we avoid retraining and inherit the full creative breadth of state-of-the-art models. Our approach generalizes across diverse backbones and 360 generation modalities. We demonstrate this across text-to-panorama using Flux.1, Flux.2, and LTX-Video backbones, achieving competitive performance against baselines, all while remaining training-free. Project page: https://orhir.github.io/SpheRoPE","short_abstract":"We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization, or leverage multi-s...","url_abs":"https://arxiv.org/abs/2606.32033","url_pdf":"https://arxiv.org/pdf/2606.32033v1","authors":"[\"Or Hirschorn\",\"Aaron Olender\",\"Eli Alshan\",\"Ianir Ideses\",\"Lior Fritz\",\"Sagie Benaim\"]","published":"2026-06-30T17:57:04Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}