3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration
- URL: http://arxiv.org/abs/2403.11577v1
- Date: Mon, 18 Mar 2024 08:53:03 GMT
- Title: 3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration
- Authors: Quentin Herau, Moussab Bennehar, Arthur Moreau, Nathan Piasco, Luis Roldao, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, Cédric Demonceaux,
- Abstract summary: We propose a new calibration method that relies on the speed and rendering accuracy of 3D Gaussian Splatting to achieve multimodal calibration.
We demonstrate the superiority of our proposal with experimental results on sequences from KITTI-360, a widely used driving dataset.
- Score: 9.825752747213297
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Reliable multimodal sensor fusion algorithms re- quire accurate spatiotemporal calibration. Recently, targetless calibration techniques based on implicit neural representations have proven to provide precise and robust results. Nevertheless, such methods are inherently slow to train given the high compu- tational overhead caused by the large number of sampled points required for volume rendering. With the recent introduction of 3D Gaussian Splatting as a faster alternative to implicit representation methods, we propose to leverage this new ren- dering approach to achieve faster multi-sensor calibration. We introduce 3DGS-Calib, a new calibration method that relies on the speed and rendering accuracy of 3D Gaussian Splatting to achieve multimodal spatiotemporal calibration that is accurate, robust, and with a substantial speed-up compared to methods relying on implicit neural representations. We demonstrate the superiority of our proposal with experimental results on sequences from KITTI-360, a widely used driving dataset.
Related papers
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction [53.19869886963333]
3D Gaussian splatting (3DGS) has shown promising results in rendering image and surface reconstruction.
This paper introduces R2-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction.
arXiv Detail & Related papers (2024-05-31T08:39:02Z) - LP-3DGS: Learning to Prune 3D Gaussian Splatting [71.97762528812187]
We propose learning-to-prune 3DGS, where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically.
Experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
arXiv Detail & Related papers (2024-05-29T05:58:34Z) - latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction [48.86083272054711]
latentSplat is a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture.
We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
arXiv Detail & Related papers (2024-03-24T20:48:36Z) - CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field [46.8198987091734]
This paper presents an efficient dense RGB-D SLAM system, i.e., CG-SLAM, based on a novel uncertainty-aware 3D Gaussian field.
Experiments on various datasets demonstrate that CG-SLAM achieves superior tracking and mapping performance with a notable tracking speed of up to 15 Hz.
arXiv Detail & Related papers (2024-03-24T11:19:59Z) - GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques.
We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians.
Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
arXiv Detail & Related papers (2024-02-22T16:00:20Z) - GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis [70.24111297192057]
We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner.
The proposed method enables 2K-resolution rendering under a sparse-view camera setting.
arXiv Detail & Related papers (2023-12-04T18:59:55Z) - GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system.
Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering.
Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
arXiv Detail & Related papers (2023-11-20T12:08:23Z) - ACSC: Automatic Calibration for Non-repetitive Scanning Solid-State
LiDAR and Camera Systems [11.787271829250805]
Solid-State LiDAR (SSL) enables low-cost and efficient obtainment of 3D point clouds from the environment.
We propose a fully automatic calibration method for the non-repetitive scanning SSL and camera systems.
We evaluate the proposed method on different types of LiDAR and camera sensor combinations in real conditions.
arXiv Detail & Related papers (2020-11-17T09:11:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.