paper-with-me

Papers

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

2025-01-28 · Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Philipp Henzler, Konrad Schindler, Federico Tombari

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/

📄 PDF Abstract BibTeX arXiv:2501.17162

Code (0)

등록된 구현이 없습니다.

Tasks

3D Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Taming Stable Diffusion for Text to 360 Panorama Image Generation

2024-01-01 · CVPR 2024 1 · Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang 외

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 Generation

Taming Stable Diffusion for Text to 360° Panorama Image Generation

2024-04-11 · Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang 외

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 Generation

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

2023-07-03 · NeurIPS 2023 11 · Shitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang 외

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 Generation

Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models

2023-11-22 · Mengyang Feng, Jinlin Liu, Miaomiao Cui, Xuansong Xie

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 Generation

Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas

2024-08-28 · Fabio Quattrini, Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara

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