Squaring-the-Sphere: Distortion-Free and Seamless Panorama Generation via CubeAtlas

Xuhui Zuo; Chenjie Cao; Tengfei Wang; Junta Wu; Yisu Zhang; Chunchao Guo

cs.CVOct 22, 2026

Squaring-the-Sphere: Distortion-Free and Seamless Panorama Generation via CubeAtlas

Authors: Xuhui Zuo, Chenjie Cao, Tengfei Wang, Junta Wu, Yisu Zhang, Chunchao Guo

Organizations: Tencent

Abstract

Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables seamless panorama modeling but suffers from severe distortion and a domain gap to pre-trained image generators, whereas cubemaps preserve perspective geometry but often produce inconsistent faces and visible seams. We present Squaring-the-Sphere, a panoramic image generation framework built on a novel representation CubeAtlas, which unfolds all cubemap faces into a single compact canvas. By arranging orientation-aligned, rotated polar regions alongside the equatorial faces, this representation preserves the perspective geometry of cubemaps while organizing the cross-face relationships required for seamless panorama assembly. It further enables a pretrained diffusion transformer to model the complete panorama jointly in a single pass, without altering the backbone architecture or positional encoding. While CubeAtlas has a token count comparable to ERP, its structured layout makes many dense attention interactions unnecessary. We therefore introduce a layout-aware sparse attention mask that preserves the interactions required for panorama continuity while removing geometrically irrelevant token pairs. As a result, CubeAtlas achieves better quality than ERP modeling with lower attention computation. Furthermore, we introduce a training-free super-resolution technique and a fusion scheme that enhance fine details in distortion-free perspective space before achieving the final ERP panorama. Experiments on various benchmarks demonstrate that our method improves geometric fidelity, cross-view consistency, and high-resolution visual quality over previous methods.

Figures & tables

Figure 1: Squaring-the-Sphere reconciles global panorama continuity with perspective-face geometry. Upper: ERP represents the full panorama on a single canvas but severely stretches the polar regions; cubemaps preserve perspective geometry but introduce disconnected face boundaries. CubeAtlas packs the four equatorial faces and rotated half-polar regions into a compact canvas, making their geometric adjacencies local for joint generation. Lower: Squaring-the-Sphere produces seamless, geometrically coherent panoramas across diverse indoor and outdoor scenes, shown as ERP renderings with perspective crops.

Figure 2: CubeAtlas representation. Four equatorial faces are unfolded into the central band. The upper and lower faces are rotated into orientation-aligned half-polar copies and placed next to their corresponding equatorial faces, forming a compact layout for joint generation.

Figure 3: Overview of Squaring-the-Sphere . Given a perspective image and text prompts, the DiT denoises the complete CubeAtlas in a single pass. Layout-aware sparse attention retains within-band interactions while restricting cross-latitude communication: for each pole, an equatorial region attends only to the two axis-aligned half-polar regions that reconstruct a complete polar face. The generated CubeAtlas is then fused and stitched into the final ERP panorama.

Figure 4: The direction-aware polar blending mask.

Self-Collected
Method	FID $\downarrow$	KID $\downarrow$	CLIP-FID $\downarrow$	Seam ${}_{\text{ERP}}$ $\downarrow$	Seam ${}_{\text{Cube}}$ $\downarrow$	Eq-IQ $\uparrow$	Eq-Aes $\uparrow$	Eq-GI $\uparrow$	Pole-IQ $\uparrow$	Pole-GI $\uparrow$	TextAdh $\uparrow$
CubeDiff	-	-	-	0.0126	0.0361	3.685	3.565	3.465	3.780	3.725	4.100
DreamCube	-	-	-	0.0279	0.0445	2.730	2.605	2.607	2.870	2.935	3.490
HunyuanPano	-	-	-	0.0154	-	4.475	4.247	4.468	4.495	4.120	4.300
HY-Pano-2.0	-	-	-	0.0199	-	4.580	4.355	4.480	4.705	4.685	4.470
Ours	-	-	-	0.0142	0.0132	4.690	4.402	4.782	4.675	4.730	4.640

Table 1: Quantitative image-to-panorama comparison on our self-collected set, RealSee3D, Laval-Indoor, and SUN360. FID, KID, and CLIP-FID are evaluated by

90^{\circ}

perspective views split along

12

icosahedral directions (eight valid directions for Laval-Indoor) and are not reported on the self-collected set without ground-truth ERPs. Seam

{}_{\text{Cube}}

is reported only for methods with native cube-face outputs.

Figure 5: Qualitative comparison with perspective cubemaps. Our results enjoy superior cross-face structures and pole geometry compared to ERP-native and cubemap-based baselines.

Variant	Tokens	Time	$\text{Seam}_{\text{ERP}}\downarrow$	$\text{Seam}_{\text{Cube}}\downarrow$	Eq-IQ $\uparrow$	Eq-Aes $\uparrow$	Eq-GI $\uparrow$	Pole-IQ $\uparrow$	Pole-GI $\uparrow$	TextAdh $\uparrow$
	Computational Profile		Quality and Continuity
ERP	$1.00\times$	$1.00\times$	0.0209	–	4.607	4.370	4.575	4.690	4.660	4.550
Cubemap	$0.75\times$	$0.76\times$	0.0147	0.0260	4.428	4.270	4.332	4.490	4.455	4.560
CubeAtlas	$1.00\times$	$1.00\times$	0.0103	0.0143	4.697	4.353	4.690	4.705	4.705	4.640
+ Sparse Attn.	$1.00\times$	$0.84\times$	0.0142	0.0132	4.690	4.402	4.782	4.675	4.730	4.640

Table 2: Ablation on panorama representation and efficiency-oriented designs. “Tokens” denotes the target-token sequence length, and “Time” denotes denoising time under the same settings. Both are reported as relative multipliers normalized to the ERP baseline (

1.00\times

). “Sparse Attn.” indicates the layout-aware sparse attention used by Squaring-the-Sphere .

Figure 6: Visual comparison of panorama representations. CubeAtlas reduces cubemap face discontinuities while preserving polar structures more faithfully than direct ERP generation.

Figure 7: Qualitative comparison of panoramic super-resolution. Our method recovers sharper details while maintaining cross-face consistency.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8: User study. Each stacked bar summarizes $700$ valid judgments comparing Squaring-the-Sphere (solid blue) with one competitor (light fill with a dashed border). The vertical dashed line denotes the $50\%$ equal-preference reference.

Figure 9: Examples of VLM-based evaluation. Regional examples show rationales and scores for the Front and Zenith views. “Distortion” denotes geometric integrity (GI), with higher scores indicating fewer artifacts. Equatorial views are rearranged for display, and the input caption is excerpted.

Metric	Eq-IQ	Eq-Aes	Pole-IQ	Eq-GI	Pole-GI	TextAdh
Spearman $\rho$	0.9358	0.8820	0.8757	0.9281	0.7698	0.8804

Appendix

Table 3: Agreement between VLM scores and human judgments. Spearman rank correlations between VLM scores and human MOS on 30 generated panoramas, each evaluated by three raters. Higher values indicate stronger rank agreement with human judgments.

Variant	Tokens	Time	Seam ${}_{\mathrm{ERP}}\downarrow$	Seam ${}_{\mathrm{Cube}}\downarrow$	Eq-IQ $\uparrow$	Eq-Aes $\uparrow$	Eq-GI $\uparrow$	Pole-IQ $\uparrow$	Pole-GI $\uparrow$	TextAdh $\uparrow$
	Computational Profile		Quality and Continuity
Half-polar	$1.00\times$	$1.00\times$	0.0103	0.0143	4.697	4.353	4.690	4.705	4.705	4.640
+ Sparse Attn.	$1.00\times$	$0.84\times$	0.0142	0.0132	4.690	4.402	4.782	4.675	4.730	4.640
Full-polar	$1.50\times$	$1.63\times$	0.0106	0.0134	4.610	4.410	4.670	4.660	4.710	4.580
+ Sparse Attn.	$1.50\times$	$1.15\times$	0.0103	0.0136	4.620	4.410	4.720	4.660	4.680	4.620

Appendix

Table 4: Full-polar vs half-polar packing. Padding tokens are omitted from the token length counting for simplification. “+ Sparse Attn.” denotes layout-aware sparse attention.

Figure 10: Additional qualitative comparisons on Laval-Indoor, SUN360, and RealSee3D. Results are shown for Squaring-the-Sphere , HY-Pano-2.0, HunyuanPano, DreamCube, and CubeDiff.

Figure 11: Additional qualitative results for high-resolution synthesis. From left to right: Native Sampling, ERP-domain SR, perspective-space SR without overlap fusion, and the complete super-resolution pipeline. Enlarged crops compare local detail recovery and cross-view consistency.

Figure 12: Panorama generation from diverse input viewing directions. Each row shows a perspective input (left) and the generated ERP panorama (right). Our method accommodates downward- and upward-looking inputs without camera calibration or explicit input projection. Red outlines indicate the corresponding input regions in the generated panoramas.

Figure 13: More qualitative results from Squaring-the-Sphere . We show diverse indoor and outdoor scenes with realistic and stylized appearances. The generated panoramas preserve the conditioning content and visual style while maintaining coherent structures throughout the complete $360^{\circ}$ FoV.

Image Generation

Image generation studies models that create or edit images from text, examples, layouts, and other structured controls.

See all 463 papers

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
Jun 30, 2026Or Hirschorn, Aaron Olender, Eli Alshan +3Video-Reference Video Generation Rotary Positional Embeddings
1Amazon Prime Video · 2Tel-Aviv University · 3Hebrew University of Jerusalem
Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion
Mar 24, 2026Yuqin Lu, Haofeng Liu, Yang Zhou +4Diffusion Models Diffusion Models for Image Restoration
SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360 $^\circ$ Panorama Generation
Jun 10, 2026Jungwoon Kang, Jaehun Kim, Yiwon Yu +3Rotary Positional Embeddings Image Generation
Yonsei University

Jun 30, 2026J/K move · Enter open · S save

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

Or Hirschorn, Aaron Olender, Eli Alshan, Ianir Ideses+2

1Amazon Prime Video · 2Tel-Aviv University · 3Hebrew University of Jerusalem

Video-Reference Video Generation Rotary Positional Embeddings Diffusion Model Guidance Diffusion Transformer Image Generation Video Generation

Open paper AskPDF arXiv

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

Abstract

Image Generation

Explore similar work

SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE

Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion

SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360∘^\circ∘ Panorama Generation

SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360 $^\circ$ Panorama Generation