Extrapolated Urban View Synthesis Benchmark
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_ | 1866910872226496512 |
|---|---|
| author | Han, Xiangyu Jia, Zhen Li, Boyi Wang, Yan Ivanovic, Boris You, Yurong Liu, Lingjie Wang, Yue Pavone, Marco Feng, Chen Li, Yiming |
| author_facet | Han, Xiangyu Jia, Zhen Li, Boyi Wang, Yan Ivanovic, Boris You, Yurong Liu, Lingjie Wang, Yue Pavone, Marco Feng, Chen Li, Yiming |
| contents | Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs. Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes. However, their performance is commonly evaluated using an interpolated setup with highly correlated training and test views. In contrast, extrapolation, where test views largely deviate from training views, remains underexplored, limiting progress in generalizable simulation technology. To address this gap, we leverage publicly available AV datasets with multiple traversals, multiple vehicles, and multiple cameras to build the first Extrapolated Urban View Synthesis (EUVS) benchmark. Meanwhile, we conduct both quantitative and qualitative evaluations of state-of-the-art NVS methods across different evaluation settings. Our results show that current NVS methods are prone to overfitting to training views. Besides, incorporating diffusion priors and improving geometry cannot fundamentally improve NVS under large view changes, highlighting the need for more robust approaches and large-scale training. We will release the data to help advance self-driving and urban robotics simulation technology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05256 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Extrapolated Urban View Synthesis Benchmark Han, Xiangyu Jia, Zhen Li, Boyi Wang, Yan Ivanovic, Boris You, Yurong Liu, Lingjie Wang, Yue Pavone, Marco Feng, Chen Li, Yiming Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs. Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes. However, their performance is commonly evaluated using an interpolated setup with highly correlated training and test views. In contrast, extrapolation, where test views largely deviate from training views, remains underexplored, limiting progress in generalizable simulation technology. To address this gap, we leverage publicly available AV datasets with multiple traversals, multiple vehicles, and multiple cameras to build the first Extrapolated Urban View Synthesis (EUVS) benchmark. Meanwhile, we conduct both quantitative and qualitative evaluations of state-of-the-art NVS methods across different evaluation settings. Our results show that current NVS methods are prone to overfitting to training views. Besides, incorporating diffusion priors and improving geometry cannot fundamentally improve NVS under large view changes, highlighting the need for more robust approaches and large-scale training. We will release the data to help advance self-driving and urban robotics simulation technology. |
| title | Extrapolated Urban View Synthesis Benchmark |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2412.05256 |