GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913313705689088 |
|---|---|
| author | Xiong, Butian Zheng, Nanjun Liu, Junhua Li, Zhen |
| author_facet | Xiong, Butian Zheng, Nanjun Liu, Junhua Li, Zhen |
| contents | We introduce a novel, multimodal large-scale scene reconstruction benchmark that utilizes newly developed 3D representation approaches: Gaussian Splatting and Neural Radiance Fields (NeRF). Our expansive U-Scene dataset surpasses any previously existing real large-scale outdoor LiDAR and image dataset in both area and point count. GauU-Scene encompasses over 6.5 square kilometers and features a comprehensive RGB dataset coupled with LiDAR ground truth. Additionally, we are the first to propose a LiDAR and image alignment method for a drone-based dataset. Our assessment of GauU-Scene includes a detailed analysis across various novel viewpoints, employing image-based metrics such as SSIM, LPIPS, and PSNR on NeRF and Gaussian Splatting based methods. This analysis reveals contradictory results when applying geometric-based metrics like Chamfer distance. The experimental results on our multimodal dataset highlight the unreliability of current image-based metrics and reveal significant drawbacks in geometric reconstruction using the current Gaussian Splatting-based method, further illustrating the necessity of our dataset for assessing geometry reconstruction tasks. We also provide detailed supplementary information on data collection protocols and make the dataset available on the following anonymous project page |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04880 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF Xiong, Butian Zheng, Nanjun Liu, Junhua Li, Zhen Computer Vision and Pattern Recognition We introduce a novel, multimodal large-scale scene reconstruction benchmark that utilizes newly developed 3D representation approaches: Gaussian Splatting and Neural Radiance Fields (NeRF). Our expansive U-Scene dataset surpasses any previously existing real large-scale outdoor LiDAR and image dataset in both area and point count. GauU-Scene encompasses over 6.5 square kilometers and features a comprehensive RGB dataset coupled with LiDAR ground truth. Additionally, we are the first to propose a LiDAR and image alignment method for a drone-based dataset. Our assessment of GauU-Scene includes a detailed analysis across various novel viewpoints, employing image-based metrics such as SSIM, LPIPS, and PSNR on NeRF and Gaussian Splatting based methods. This analysis reveals contradictory results when applying geometric-based metrics like Chamfer distance. The experimental results on our multimodal dataset highlight the unreliability of current image-based metrics and reveal significant drawbacks in geometric reconstruction using the current Gaussian Splatting-based method, further illustrating the necessity of our dataset for assessing geometry reconstruction tasks. We also provide detailed supplementary information on data collection protocols and make the dataset available on the following anonymous project page |
| title | GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRF |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.04880 |