CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

N Kalischek, M Oechsle, F Manhardt… - The Thirteenth …, 2025 - openreview.net
We introduce a novel method for generating 360° panoramas from text prompts or images.
Our approach leverages recent advances in 3D generation by employing multi-view …

Bridging Global Context Interactions for High-Fidelity Pluralistic Image Completion

C Zheng, G Song, TJ Cham, J Cai… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We introduce PICFormer, a novel framework for P luralistic I mage C ompletion using a trans
Former based architecture, that achieves both high quality and diversity at a much faster …

OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation

W Li, S Zhao, C Mou, X Sheng, Z Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
As virtual reality gains popularity, the demand for controllable creation of immersive and
dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV …

PanoDreamer: 3D Panorama Synthesis from a Single Image

A Paliwal, X Zhou, A Tsarov, NK Kalantari - arxiv preprint arxiv …, 2024 - arxiv.org
In this paper, we present PanoDreamer, a novel method for producing a coherent 360$^\circ
$ 3D scene from a single input image. Unlike existing methods that generate the scene …

A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision

H Ai, Z Cao, L Wang - arxiv preprint arxiv:2502.10444, 2025 - arxiv.org
Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much
wider than the pinhole cameras and captures richer surrounding environment details than …

CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model

X Yuan, S Tang, K Li, A Yuille, P Wang - arxiv preprint arxiv:2407.07174, 2024 - arxiv.org
This paper introduces Camera-free Diffusion (CamFreeDiff) model for 360-degree image
outpainting from a single camera-free image and text description. This method distinguishes …

PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs

T Zhou, X Zhang, Y Tang - arxiv preprint arxiv:2411.15867, 2024 - arxiv.org
Panoramic Image Generation has emerged as an important task in image generation, driven
by growing demands for large-scale visuals in creative and technical applications. While …

VideoPanda: Video Panoramic Diffusion With Multi-view Attention

K **e, A Sabour, J Huang, D Paschalidou, U Iqbal… - openreview.net
High resolution panoramic video content is paramount for immersive experiences in Virtual
Reality, but is non-trivial to collect as it requires specialized equipment and intricate camera …