- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents SpheRoPE, a training-free and optimization-free framework for generating 360° panoramic images and videos using pretrained diffusion transformers. It modifies the horizontal rotary positional embeddings through spectral partitioning: high-frequency channels are quantized to integer-period harmonics to enforce horizontal periodicity, while low-frequency channels use spherical Cartesian coordinates to capture spherical topology and polar convergence. The framework also introduces Semantic Distortion CFG, which uses the prediction difference between a content prompt and its geometry-augmented version to strengthen equirectangular projection characteristics.
Critical strengths
- It’s interesting that training-free methods can leverage the capabilities of foundation models to directly improve panoramic generation results.
- The paper is clearly written and easy to follow.
Critical weaknesses
- SHERPA [1] also modifies only the high-frequency horizontal RoPE channels, rounding the frequencies to integer-period harmonics. Under the minimum-cycle condition required by SpheRoPE, the quantization formulas for the high-frequency components of the two methods are equivalent. Furthermore, without training, it leads to a decrease in overall FAED and FID. For boundary connectivity, works such as 360DVD [2] and SphereDiffusion [3] have proposed rotating while denoising. Can modifying positional encoding provide better gains than these methods?
- In the comparison with other methods, the video foundation model used is LTX 2.3, while the compared methods mostly use AnimateDiff (360DVD), VideoCrafter (DynamicScaler), Wan2.1 (PanoWan), and LTX Video (SphereDiff). There is insufficient evidence to convincingly establish whether the improvements come from the proposed method or a stronger generative foundation model.
- Semantic Distortion CFG concatenates geometric descriptions to the same content prompt and then uses the difference between two conditional predictions to enhance ERP attributes. The application design is reasonable, but its novelty as a general method is limited, constituting a simple modification of Composable Diffusion [4] and SEGA [5] for spherical geometry.
[1] SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360° Panorama Generation
[2] 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model
[3] SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation
[4] Compositional Visual Generation with Composable Diffusion Models
[5] SEGA: Instructing Text-to-Image Models using Semantic Guidance
Questions for authors
See WeakNess
5 comments
Video Foundation Model Comparison (W2)
To isolate our contribution on matched video backbones, we compare vanilla LTX 2.3 with our Table 2 row (identical prompts, sampler, and seeds) and evaluate our method zero-shot on Wan2.1-T2V-1.3B [4], PanoWan's exact checkpoint and prompts, plus the full method on Wan2.1-14B at 1440×720:
| Set | Method | IQ↑ | CLIP↑ | Flicker↑ | Motion↑ | Subj.↑ | BG↑ | Seam DS↓ |
|---|---|---|---|---|---|---|---|---|
| SphereDiff-20 | Vanilla LTX 2.3 | 53.15 | 26.64 | 99.17 | 99.45 | 93.31 | 95.42 | 6.44 |
| Ours (Table 2) | 53.64 | 27.95 | 99.58 | 99.62 | 98.22 | 97.71 | 1.03 | |
| Stress-20 | Vanilla LTX 2.3 | 43.60 | 29.34 | 96.63 | 98.54 | 86.59 | 91.54 | 10.57 |
| Ours (Table 2) | 51.76 | 28.91 | 98.91 | 99.46 | 96.51 | 96.02 | 1.48 |
| Set | Method | IQ↑ | CLIP↑ | Flicker↑ | Motion↑ | Subj.↑ | BG↑ | Seam DS↓ | Pole std↓ |
|---|---|---|---|---|---|---|---|---|---|
| SphereDiff-20 | PanoWan (1.3B, LoRA) | 39.10 | 27.32 | 99.13 | 99.43 | 97.40 | 96.59 | 0.84 | 3.8/7.2 |
| Stock Wan2.1-1.3B | 44.73 | 26.81 | 98.69 | 99.18 | 95.75 | 95.89 | 12.33 | 15.2/21.9 | |
| Ours (1.3B, cyclic) | 45.19 | 26.72 | 98.71 | 99.17 | 96.75 | 95.96 | 1.12 | 14.9/20.3 | |
| Ours (14B, full) | 48.40 | 26.18 | 98.54 | 99.08 | 95.07 | 94.99 | 0.88 | 1.3/4.1 | |
| Stress-20 | PanoWan (1.3B, LoRA) | 39.49 | 28.42 | 97.11 | 98.58 | 91.64 | 93.66 | 0.98 | 8.1/10.0 |
| Stock Wan2.1-1.3B | 41.42 | 27.00 | 94.23 | 96.32 | 85.64 | 91.88 | 20.47 | 34.0/34.4 | |
| Ours (1.3B, cyclic) | 44.06 | 26.59 | 95.31 | 97.11 | 88.83 | 92.44 | 1.24 | 37.8/35.1 | |
| Ours (14B, full) | 44.17 | n/a | 97.77 | 98.48 | 91.01 | 93.13 | 0.85 | 2.6/2.3 |
Real ODI-SR panoramas have Pole std 6.0/11.4.
Takeaway: Against vanilla LTX 2.3, SpheRoPE improves all 6 VBench metrics on SphereDiff-20 and 5/6 on Stress-20 while closing the wrap seam (DS 6.44 → 1.03, 10.57 → 1.48). On Wan2.1-1.3B, our method closes the seam of the stock checkpoint (12.33 → 1.12, 20.47 → 1.24) and improves IQ and consistency. Panoramic video fine-tuning gives PanoWan a tighter seam and higher temporal stability and CLIP (+0.6 to +1.8) but degrades visual quality (IQ 44.73 on Stock vs. 39.10 on PanoWan), whereas we preserve visual fidelity (+6.09 and +4.57 IQ over PanoWan).
Scope on the 1.3B checkpoint: this small model relies on its lowest-frequency width channels for horizontal layout, and the spherical band collapses its generation. We therefore use a cyclic integer variant of our width encoding, which closes the seam but does not converge the poles. On Wan2.1-14B the full method works and gives the best poles on both sets and the best Stress-20 seam.
Regarding the role of the backbone: comparing zero-shot results with models trained on panoramic data is inherently unfavorable to us, so the direct comparisons are against the plain backbone (above). SpheRoPE also composes with training (LoRA fine-tuning FLUX.2 with SpheRoPE lowers FID from 25.33 to 16.63, App. B.5), and a training-free method leverages stronger backbones as soon as they are released.
Novelty of Semantic Distortion CFG (W3)
We thank the reviewer for pointing out Composable Diffusion [5] and SEGA [6], and will cite both in Sec. 2 and 3.3. While SD-CFG is an important component for leveraging pretrained ERP priors, our key novelty is Spherical RoPE (Sec. 3.2): without it, the seam degrades on both backbones (DS 0.94 → 1.22 on FLUX.2, Table 4, and 0.89 → 1.42 on FLUX.1) and on FLUX.1 the poles do not converge (Pole std 30.6/34.2 vs. 4.0/11.1, see W1). Moreover, unlike Composable Diffusion [5], which combines independent prompts ε(p_1) and ε(p_2), conditioning on p_geo alone injects conflicting scene content (Sec. 3.3). Anchoring via p_anchor = [p, p_geo] and computing ε([p, p_geo]) − ε(p) isolates the pure ERP geometric deformation for the target scene. Appending p_geo under standard CFG is the coupled special case γ = w_sem. In Table 4's setting it reaches FAED 33.33 and DS 0.99, vs. 25.40 and 0.94 with decoupled γ (see response to r3P5).
Changes in the revision:
- SHERPA and rotate-while-denoising discussed in Sec. 2, with the SHERPA control and the image and video rotation comparisons in the appendix.
- Vanilla LTX 2.3 and Wan2.1 rows in Table 2.
- Composable Diffusion and SEGA cited in Sec. 2 and 3.3.
We thank the reviewer once again and hope these responses address all concerns.
[4] Team Wan, "Wan: Open and Advanced Large-Scale Video Generative Models," arXiv:2503.20314, 2025.
[5] Liu et al., "Compositional Visual Generation with Composable Diffusion Models," ECCV 2022.
[6] Brack et al., "SEGA: Instructing Text-to-Image Models using Semantic Guidance," NeurIPS 2023.
Dear Reviewer KFg1,
We thank you once again for your insightful feedback on our paper.
As the Author-Reviewer discussion period is drawing to a close, we would like to ask whether our responses have adequately addressed your concerns. Following your comments, we compared against SHERPA's encoding and rotate-while-denoising on the same backbone, for both images and video, added backbone-matched video results (vanilla LTX 2.3 and Wan2.1), and clarified the novelty of SD-CFG relative to Composable Diffusion and SEGA. We would be happy to clarify anything further. We greatly appreciate your time and consideration.
Best, Authors
We thank the reviewer for the positive evaluation and for highlighting the clarity and value of our training-free approach. Below we address the raised concerns.
Comparison with Concurrent SHERPA and Rotate-While-Denoising (W1)
We compare SHERPA's encoding without its adapters (its 14 highest-frequency width pairs snapped, the rest linear) and rotate-while-denoising (a π/2 latent roll at every step) on the same backbone and recipe: FLUX.1 with SD-CFG and circular padding, n = 1,200. We also report Pole std (pixel std along top/bottom rows, 0 for an exact pole C2, and 6.0/11.4 on real panoramas), Polar FID (FID over the eight ±60°-pitch views), and Seam-FID (FID of crops centered on the wrap):
Concurrent SHERPA [1] (trained vs. zero-shot): SHERPA is concurrent work and is training-based (trained adapters on FLUX.1), whereas SpheRoPE is zero-shot. While both snap high-frequency width channels to integer harmonics, SHERPA leaves the low-frequency band linear, which provides neither periodicity nor polar convergence (C2) in the low band, relying on trained adapters to learn the poles and global layout. Without the adapters, this encoding closes the border seam (DS 0.92) but not the poles (Pole std 19.1/27.3 vs. 4.0/11.1 for SpheRoPE, Polar FID 66.8 vs. 47.9), and snapping its lower pairs costs view quality (FID 51.48 vs. 45.22), so the poles need our low-frequency spherical band. Snapping low frequencies instead causes large OOD shifts that break global layout (Fig. 7a). Our low-frequency spherical Cartesian encoding satisfies both C1 and C2 without training (DS 0.89, Pole std 4.0/11.1, Polar FID 47.9).
Rotate-while-denoising [2]: Rolling the latent between steps (as in 360DVD [2], whereas SphereDiff [3] fuses perspective views rather than rotating) only relocates the seam between steps: within every forward pass, planar RoPE still treats the current borders as distant and provides zero polar convergence (C2). In Table 2, ours scores above 360DVD on all six VBench dimensions on both prompt sets, and above DynamicScaler (window shifting) on all six on SphereDiff-20, at a fraction of SphereDiff's and DynamicScaler's cost.
True polar convergence (C2): Rotation leaves the poles unconverged (Pole std 17.3/26.0 vs. 4.0/11.1 for SpheRoPE, close to real panoramas at 6.0/11.4). Polar views confirm it: across the eight ±60°-pitch views, SpheRoPE lowers FID from 60.0 to 47.9 and KID×10² from 2.82 to 1.69, and on zenith/nadir faces lowers KID×10² from 3.05 to 1.54 and 4.75 to 4.20. Global FAED ranks the other rows higher but, as with vanilla FLUX.1 (see our response to r3P5), barely registers unconverged poles.
Sharper cross-seam and view quality: While rotation blends pixel differences at the border (DS 0.88 vs. 0.89), planar attention blurs content across the wrap (Seam-FID 50.91 vs. 42.75 for SpheRoPE) and degrades per-view FID/KID/IS.
The same holds for video on LTX 2.3 (Table 2 settings), where SpheRoPE outperforms rotation on temporal stability, subject/background consistency, seam continuity (DS), and polar convergence (Pole std) across both sets:
[1] Kang et al., "SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360° Panorama Generation," 2026.
[2] Wang et al., "360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model," CVPR 2024.
[3] Park et al., "SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation," AAAI 2026.