Skyeyes: Ground Roaming using Aerial View Images
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912045737181184 |
|---|---|
| author | Gao, Zhiyuan Teng, Wenbin Chen, Gonglin Wu, Jinsen Xu, Ningli Qin, Rongjun Feng, Andrew Zhao, Yajie |
| author_facet | Gao, Zhiyuan Teng, Wenbin Chen, Gonglin Wu, Jinsen Xu, Ningli Qin, Rongjun Feng, Andrew Zhao, Yajie |
| contents | Integrating aerial imagery-based scene generation into applications like autonomous driving and gaming enhances realism in 3D environments, but challenges remain in creating detailed content for occluded areas and ensuring real-time, consistent rendering. In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience. More specifically, we combine a 3D representation with a view consistent generation model, which ensures coherence between generated images. This method allows for the creation of geometrically consistent ground view images, even with large view gaps. The images maintain improved spatial-temporal coherence and realism, enhancing scene comprehension and visualization from aerial perspectives. To the best of our knowledge, there are no publicly available datasets that contain pairwise geo-aligned aerial and ground view imagery. Therefore, we build a large, synthetic, and geo-aligned dataset using Unreal Engine. Both qualitative and quantitative analyses on this synthetic dataset display superior results compared to other leading synthesis approaches. See the project page for more results: https://chaoren2357.github.io/website-skyeyes/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16685 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Skyeyes: Ground Roaming using Aerial View Images Gao, Zhiyuan Teng, Wenbin Chen, Gonglin Wu, Jinsen Xu, Ningli Qin, Rongjun Feng, Andrew Zhao, Yajie Computer Vision and Pattern Recognition Integrating aerial imagery-based scene generation into applications like autonomous driving and gaming enhances realism in 3D environments, but challenges remain in creating detailed content for occluded areas and ensuring real-time, consistent rendering. In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience. More specifically, we combine a 3D representation with a view consistent generation model, which ensures coherence between generated images. This method allows for the creation of geometrically consistent ground view images, even with large view gaps. The images maintain improved spatial-temporal coherence and realism, enhancing scene comprehension and visualization from aerial perspectives. To the best of our knowledge, there are no publicly available datasets that contain pairwise geo-aligned aerial and ground view imagery. Therefore, we build a large, synthetic, and geo-aligned dataset using Unreal Engine. Both qualitative and quantitative analyses on this synthetic dataset display superior results compared to other leading synthesis approaches. See the project page for more results: https://chaoren2357.github.io/website-skyeyes/. |
| title | Skyeyes: Ground Roaming using Aerial View Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.16685 |