CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
We introduce a novel method for generating 360{\deg} panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively. Project page: https://cubediff.github.io/
Code (0)
등록된 구현이 없습니다.
Tasks
3D GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Taming Stable Diffusion for Text to 360 Panorama Image Generation
Generative models e.g. Stable Diffusion have enabled the creation of photorealistic images from text prompts. Yet the generation of 360-degree panorama images from text remains a challenge particularly due to the dea…
DenoisingImage GenerationTaming Stable Diffusion for Text to 360° Panorama Image Generation
Generative models, e.g., Stable Diffusion, have enabled the creation of photorealistic images from text prompts. Yet, the generation of 360-degree panorama images from text remains a challenge, particularly due to the de…
DenoisingImage GenerationMVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view i…
Image GenerationDiffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models
This is a technical report on the 360-degree panoramic image generation task based on diffusion models. Unlike ordinary 2D images, 360-degree panoramic images capture the entire $360^\circ\times 180^\circ$ field of view.…
DenoisingImage GenerationMerging and Splitting Diffusion Paths for Semantically Coherent Panoramas
Diffusion models have become the State-of-the-Art for text-to-image generation, and increasing research effort has been dedicated to adapting the inference process of pretrained diffusion models to achieve zero-shot capa…
DiversityImage GenerationText to Image GenerationText-to-Image Generation