hub / github.com/Xin-Ye-1/BEVDiffuser
github.com/Xin-Ye-1/BEVDiffuser @main
Chat with this repo
795 symbols
2,898 edges
197 files
⚖ AGPL-3.0
343 documented · 43%
● updated 15mo ago★ 518 open issues
Browse by type
What it actually does AI analysis from the code graph — generated when you open this
loading…
README
BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance
CVPR 2025 Highlight
Official implementation of BEVDiffuser.
BEVDiffuser with BEVFormer
Acknowledgement
Large parts of the code base are inspied and build on top of the following projects: - BEVFormer - LayoutDiffusion - diffusers
Citation
If find this work helpful, please consider citing: (bibtex)
@InProceedings{ye2025bevdiffuser,
author={Ye, Xin and Yaman, Burhaneddin and Cheng, Sheng and Tao, Feng and Mallik, Abhirup and Ren, Liu},
title={BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
month = {June},
year = {2025}
}
Core symbols most depended-on inside this repo
↓ 39 filesTransform3d
A Transform3d object encapsulates a batch of N 3D transformations, and knows how to transform points and normal vectors. Suppose …
BEVFormer/projects/mmdet3d_plugin/dd3d/structures/transform3d.py
↓ 12 filesPoseSE(3) rigid transform class that allows compounding of 6-DOF poses and provides common transformations that are commonly seen in …
BEVFormer/projects/mmdet3d_plugin/dd3d/structures/pose.py
↓ 7 filesCustomNuScenesMonoDatasetr"""Monocular 3D detection on NuScenes Dataset. This class serves as the API for experiments on the NuScenes Dataset. Please …
BEVFormer/projects/mmdet3d_plugin/datasets/nuscenes_mono_dataset.py
↓ 5 filesNMSFreeCoderBbox coder for NMS-free detector. Args: pc_range (list[float]): Range of point cloud. post_center_range (list[float]): Limit of …
BEVFormer/projects/mmdet3d_plugin/core/bbox/coders/nms_free_coder.py
↓ 5 filesbuild_dataloaderBuild PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only …
BEVFormer/projects/mmdet3d_plugin/datasets/builder.py
↓ 4 filesWaymo2KITTIWaymo to KITTI converter. This class serves as the converter to change the waymo raw data to KITTI format. Args: load_dir (str): …
BEVFormer/tools/data_converter/waymo_converter.py
Shape
Languages
Python100%
Modules by API surface
BEVFormer/projects/mmdet3d_plugin/dd3d/structures/transform3d.py39 symbols
BEVFormer/projects/bevdiffuser/layout_diffusion/layout_diffusion_unet.py33 symbols
BEVFormer/projects/mmdet3d_plugin/dd3d/structures/boxes3d.py25 symbols
BEVFormer/projects/bevdiffuser/layout_diffusion/layout_encoder.py22 symbols
BEVFormer/projects/mmdet3d_plugin/datasets/pipelines/transform_3d.py21 symbols
BEVFormer/projects/mmdet3d_plugin/models/backbones/vovnet.py20 symbols
BEVFormer/projects/mmdet3d_plugin/datasets/nuscnes_eval.py18 symbols
BEVFormer/projects/mmdet3d_plugin/datasets/nuscenes_mono_dataset.py17 symbols
BEVFormer/projects/bevdiffuser/layout_diffusion/nn.py17 symbols
BEVFormer/tools/data_converter/scannet_data_utils.py16 symbols
BEVFormer/projects/bevdiffuser/data_utils.py16 symbols
BEVFormer/tools/data_converter/kitti_data_utils.py15 symbols
For agents
$ claude mcp add BEVDiffuser \
-- python -m otcore.mcp_server <graph>