SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors
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_ | 1866929645882966016 |
|---|---|
| author | Guo, Yijia Hu, Liwen Bai, Yuanxi Yao, Jiawei Ma, Lei Huang, Tiejun |
| author_facet | Guo, Yijia Hu, Liwen Bai, Yuanxi Yao, Jiawei Ma, Lei Huang, Tiejun |
| contents | 3D Gaussian Splatting (3DGS) demonstrates unparalleled superior performance in 3D scene reconstruction. However, 3DGS heavily relies on the sharp images. Fulfilling this requirement can be challenging in real-world scenarios especially when the camera moves fast, which severely limits the application of 3DGS. To address these challenges, we proposed Spike Gausian Splatting (SpikeGS), the first framework that integrates the spike streams into 3DGS pipeline to reconstruct 3D scenes via a fast-moving bio-inspired camera. With accumulation rasterization, interval supervision, and a specially designed pipeline, SpikeGS extracts detailed geometry and texture from high temporal resolution but texture lacking spike stream, reconstructs 3D scenes captured in 1 second. Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of SpikeGS compared with existing spike-based and deblur 3D scene reconstruction methods. Codes and data will be released soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors Guo, Yijia Hu, Liwen Bai, Yuanxi Yao, Jiawei Ma, Lei Huang, Tiejun Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) demonstrates unparalleled superior performance in 3D scene reconstruction. However, 3DGS heavily relies on the sharp images. Fulfilling this requirement can be challenging in real-world scenarios especially when the camera moves fast, which severely limits the application of 3DGS. To address these challenges, we proposed Spike Gausian Splatting (SpikeGS), the first framework that integrates the spike streams into 3DGS pipeline to reconstruct 3D scenes via a fast-moving bio-inspired camera. With accumulation rasterization, interval supervision, and a specially designed pipeline, SpikeGS extracts detailed geometry and texture from high temporal resolution but texture lacking spike stream, reconstructs 3D scenes captured in 1 second. Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of SpikeGS compared with existing spike-based and deblur 3D scene reconstruction methods. Codes and data will be released soon. |
| title | SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.03771 |