Newest papers

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

Xuhui Zuo, Chenjie Cao, Tengfei Wang, Junta Wu, Yisu Zhang, Chunchao Guo · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31565 · cited by 0 works (OpenAlex) · open-access PDF

Korean

360도 광경을 생성하는 것은 로컬 관점 충실성과 글로벌 구체 연속성 모두를 필요로합니다. 기존의 표현은 거래에 직면합니다: 정사각 관점 (ERP)은 완벽한 광경 세부 사항을 모델링 할 수 있지만 심각한 변형과 도메인 간격을 필요로합니다. 큐브맵은 방향 조정, 방향 반대 영역을 보존하지만 종종 불일치 얼굴과 시각적 얼굴을 생성합니다. 우리는 새로운 상호 작용 광경 표현 CubeAtlas에 구축 된 패널리즘 이미지 생성 프레임 워크인 스쿼링 (Squaring-the-Sphere)을 제시하지만, 이는 모든 큐브맵 얼굴을 단일 컴팩트한 패널로 개체합니다. 큐브맵은 방향 조정, 방향

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Panorama, Computer science, Computer vision, Perspective (graphical), Artificial intelligence, Fidelity

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange