Home

Awesome

<details open> <summary>FlashOcc on UniOcc and RenderOcc</summary> <details open> <summary>FlashOcc on UniOcc</summary>

(As our models on Autodl is emptied by ourselves, we are now devote to reproduce them)

Nuscenes Occupancy

Configtrain timesmIOUFPS(Hz)Flops(G)Params(M)ModelLog
UniOcc-R50-256x704-------
M4:FO(UniOcc)-R50-256x704-------
UniOcc-R50-4D-Stereo-256x704-38.46---baidubaidu
M5:FO(UniOcc)-R50-4D-Stereo-256x704-38.76---baidubaidu
Additional:FO(UniOcc)-R50-4D-Stereo-256x704(wo-nerfhead)-38.44---baidubaidu
UniOcc-STBase-4D-Stereo-512x1408-------
M6:FO(UniOcc)-STBase-4D-Stereo-512x1408-------

FPS are tested via TensorRT on 3090 with FP16 precision. Please refer to Tab.2 in paper for the detail model settings for M-number.

Acknowledgement

Many thanks to these excellent open source projects:

Related Projects:

</details> <details open> <summary>FlashOcc on RenderOcc</summary> </details> </details> <details open> <summary> Readme from ofiginal RenderOcc</summary>

RenderOcc

paper | video

demo (Visualization of RenderOcc's prediction, which is supervised only with 2D labels.)

INTRODUCTION

RenderOcc is a novel paradigm for training vision-centric 3D occupancy models only with 2D labels. Specifically, we extract a NeRF-style 3D volume representation from multi-view images, and employ volume rendering techniques to establish 2D renderings, thus enabling direct 3D supervision from 2D semantics and depth labels.

demo

Getting Started

Model Zoo

MethodBackbone2D-to-3DLr SchdGTmIoUConfigLogDownload
RenderOccSwin-BaseBEVStereo12ep2D24.46configlogmodel

Acknowledgement

Many thanks to these excellent open source projects:

Related Projects:

BibTeX

If this work is helpful for your research, please consider citing:

@article{pan2023renderocc,
  title={RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision},
  author={Pan, Mingjie and Liu, Jiaming and Zhang, Renrui and Huang, Peixiang and Li, Xiaoqi and Liu, Li and Zhang, Shanghang},
  journal={arXiv preprint arXiv:2309.09502},
  year={2023}
}
</details>