We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| georghess/voxel-mae | canonical | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| get_paddings_indicator | Ran | georghess/voxel-mae/mmdet3d/models/voxel_encoders/utils.py code served (permissive licence) · get_code("c95c785cf3afb29e") |
| points_to_voxel | Not yet run | georghess/voxel-mae/mmdet3d/core/voxel/voxel_generator.py code served (permissive licence) · get_code("9cb6f05fd5b5077e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are cheap to collect compared to annotations for tasks like 3D object detection (OD). However, the development of masked autoencoders for point clouds has focused solely on synthetic and indoor data. Consequently, existing methods have tailored their representations and models toward small and dense point clouds with homogeneous point densities. In this work, we study masked autoencoding for point clouds in an automotive setting, which are sparse and for which the point density can vary drastically among objects in the same scene. To this end, we propose Voxel-MAE, a simple masked autoencoding pre-training scheme designed for voxel representations. We pre-train the backbone of a Transformer-based 3D object detector to reconstruct masked voxels and to distinguish between empty and non-empty voxels. Our method improves the 3D OD performance by 1.75 mAP points and 1.05 NDS on the challenging nuScenes dataset. Further, we show that by pre-training with Voxel-MAE, we require only 40% of the annotated data to outperform a randomly initialized equivalent. Code available at https://github.com/georghess/voxel-mae
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.00531")
get_code_for_paper("2207.00531")
have("2207.00531")
Connect an agent — have() is free.