Please cite our paperDISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction (NeurIPS 2019) if you plan to download the rendered images or use our code to render by yourself.
@inProceedings{xu2019disn,
title={DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction},
author={Xu, Qiangeng and Wang, Weiyue and Ceylan, Duygu and Mech, Radomir and Neumann, Ulrich},
booktitle={NeurIPS},
year={2019}
}
Code contact: Qiangeng Xu* and Weiyue Wang*
Also please cite Shapenet's original paper as well.
The categories included are:
"watercraft": "04530566",
"rifle": "04090263",
"display": "03211117",
"lamp": "03636649",
"speaker": "03691459",
"cabinet": "02933112",
"chair": "03001627",
"bench": "02828884",
"car": "02958343",
"airplane": "02691156",
"sofa": "04256520",
"table": "04379243",
"phone": "04401088"
}
Our rendering is based on the convention of 3DR2N2's 2d image rendering.
albedo | RGB | Depth | normal |
---|---|---|---|
In each folder, there is a meta file: rendering_metadata.txt: each line represent a parameter:
camera Yaw | camera Roll | camera Pitch | distance ratio (0 to 1) | Focal length in mm | Sensor size in mm | max real distance | x_rand | y_rand | z_rand |
---|---|---|---|---|---|---|---|---|---|
74.77100786318874 | 37.07793266268725 | 0 | 0.6451202137421064 | 35 | 32 | 1.75 | -0.1529439091682434 | -0.13056571781635284 | 0.0746786817908287 |
install blender 2.79 and go to its python3.5m to install pip3, then install numpy and opencv
python -u render_batch --model_root_dir {model root dir} --render_root_dir {where you store images} --filelist_dir {which models you want to render} --blender_location {you} --num_thread {10} --shapenetversion {support v1, v2} --debug {False}
Please refer to cam_read.py