paper-with-me

홈 › Papers

Omni-Directional Image Generation from Single Snapshot Image

2020-10-12 · Keisuke Okubo, Takao Yamanaka

An omni-directional image (ODI) is the image that has a field of view covering the entire sphere around the camera. The ODIs have begun to be used in a wide range of fields such as virtual reality (VR), robotics, and social network services. Although the contents using ODI have increased, the available images and videos are still limited, compared with widespread snapshot images. A large number of ODIs are desired not only for the VR contents, but also for training deep learning models for ODI. For these purposes, a novel computer vision task to generate ODI from a single snapshot image is proposed in this paper. To tackle this problem, the conditional generative adversarial network was applied in combination with class-conditioned convolution layers. With this novel task, VR images and videos will be easily created even with a smartphone camera.

📄 PDF Abstract BibTeX arXiv:2010.05600

Code (2)

keisuke-okb/class-conditioned-ODI-generator-pytorch 공식 구현 pytorch
islab-sophia/odigen-mlpmixer pytorch

Tasks

Generative Adversarial NetworkImage Generation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Increasing diversity of omni-directional images generated from single image using cGAN based on MLPMixer

2023-09-15 · Atsuya Nakata, Ryuto Miyazaki, Takao Yamanaka

This paper proposes a novel approach to generating omni-directional images from a single snapshot picture. The previous method has relied on the generative adversarial networks based on convolutional neural networks (CNN…

DiversityImage Generation

Omni$^2$: Unifying Omnidirectional Image Generation and Editing in an Omni Model

2025-04-15 · Liu Yang, Huiyu Duan, Yucheng Zhu, Xiaohong Liu 외

$360^{\circ}$ omnidirectional images (ODIs) have gained considerable attention recently, and are widely used in various virtual reality (VR) and augmented reality (AR) applications. However, capturing such images is expe…

Image Generation

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

2021-04-28 · Masato Tamura, Tomoaki Yoshinaga

We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection that enables detectors to tightly fit bounding boxes to pedestrians without omnidirectional images for training. Due…

object-detectionObject DetectionPedestrian Detection

Unsupervised Bi-directional Flow-based Video Generation from one Snapshot

2019-03-03 · Lu Sheng, Junting Pan, Jiaming Guo, Jing Shao 외

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual dist…

Video Generation

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

2024-12-12 · Weiqi Li, Shijie Zhao, Chong Mou, Xuhan Sheng 외

As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, th…

Image to Video GenerationVideo Generation