RenderOcc

Paper | Video | Technical Report (UniOcc)

(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.

Getting Started

• Installation

• Prepare Dataset

• Train

  # Train RenderOcc with 8 GPUs
  ./tools/dist_train.sh ./configs/renderocc/renderocc-7frame.py 8

• Evaluation

  # Eval RenderOcc with 8 GPUs
  ./tools/dist_test.sh ./configs/renderocc/renderocc-7frame.py ./path/to/ckpts.pth 8

• Visualization

  # Dump predictions
  bash tools/dist_test.sh configs/renderocc/renderocc-7frame.py renderocc-7frame-12e.pth 1 --dump_dir=work_dirs/output
  # Visualization (select scene-id)
  python tools/visualization/visual.py work_dirs/output/scene-xxxx

  (The pkl file needs to be regenerated for visualization.)

Model Zoo

Method	Backbone	2D-to-3D	Lr Schd	GT	mIoU	Config	Log	Download
RenderOcc	Swin-Base	BEVStereo	12ep	2D	24.46	config	log	model

• More model weights will be released later.

Acknowledgement

Many thanks to these excellent open source projects:

• BEVDet, DVGO, Occ3D, SurroundDepth, OpenOccupancy, CVPR2023-Occ-Challenge

Related Projects:

• SurroundOcc, TPVFormer, BEVFormer, VoxFormer, FB-Occ, SimpleOccupancy, OVO

BibTeX

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

@inproceedings{pan2024renderocc,
  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 Xie, Hongwei and Wang, Bing and Liu, Li and Zhang, Shanghang},
  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={12404--12411},
  year={2024},
  organization={IEEE}
}