GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908499719487488 |
|---|---|
| author | Boeder, Simon Gigengack, Fabian Risse, Benjamin |
| author_facet | Boeder, Simon Gigengack, Fabian Risse, Benjamin |
| contents | Occupancy estimation has become a prominent task in 3D computer vision, particularly within the autonomous driving community. In this paper, we present a novel approach to occupancy estimation, termed GaussianFlowOcc, which is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation. Our efficient model architecture based on a Gaussian Transformer significantly reduces computational and memory requirements by eliminating the need for expensive 3D convolutions used with inefficient voxel-based representations that predominantly represent empty 3D spaces. GaussianFlowOcc effectively captures scene dynamics by estimating temporal flow for each Gaussian during the overall network training process, offering a straightforward solution to a complex problem that is often neglected by existing methods. Moreover, GaussianFlowOcc is designed for scalability, as it employs weak supervision and does not require costly dense 3D voxel annotations based on additional data (e.g., LiDAR). Through extensive experimentation, we demonstrate that GaussianFlowOcc significantly outperforms all previous methods for weakly supervised occupancy estimation on the nuScenes dataset while featuring an inference speed that is 50 times faster than current SOTA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17288 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow Boeder, Simon Gigengack, Fabian Risse, Benjamin Computer Vision and Pattern Recognition Occupancy estimation has become a prominent task in 3D computer vision, particularly within the autonomous driving community. In this paper, we present a novel approach to occupancy estimation, termed GaussianFlowOcc, which is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation. Our efficient model architecture based on a Gaussian Transformer significantly reduces computational and memory requirements by eliminating the need for expensive 3D convolutions used with inefficient voxel-based representations that predominantly represent empty 3D spaces. GaussianFlowOcc effectively captures scene dynamics by estimating temporal flow for each Gaussian during the overall network training process, offering a straightforward solution to a complex problem that is often neglected by existing methods. Moreover, GaussianFlowOcc is designed for scalability, as it employs weak supervision and does not require costly dense 3D voxel annotations based on additional data (e.g., LiDAR). Through extensive experimentation, we demonstrate that GaussianFlowOcc significantly outperforms all previous methods for weakly supervised occupancy estimation on the nuScenes dataset while featuring an inference speed that is 50 times faster than current SOTA. |
| title | GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.17288 |