Repository files navigation

This is the official implementation ofNeuralangelo: High-Fidelity Neural Surface Reconstruction.

Zhaoshuo Li,Thomas Müller,Alex Evans,Russell H. Taylor,Mathias Unberath,Ming-Yu Liu,Chen-Hsuan Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

The code is built upon the Imaginaire library from the Deep Imagination Research Group at NVIDIA.
For business inquiries, please submit theNVIDIA research licensing form.

We offer two ways to setup the environment:

1. We provide prebuilt Docker images, where

   • docker.io/chenhsuanlin/colmap:3.8 is for running COLMAP and the data preprocessing scripts. This includes the prebuilt COLMAP library (CUDA-supported).
   • docker.io/chenhsuanlin/neuralangelo:23.04-py3 is for running the main Neuralangelo pipeline.

   The corresponding Dockerfiles can be found in thedocker directory.

2. The conda environment for Neuralangelo. Install the dependencies and activate the environmentneuralangelo with

   conda env create --file neuralangelo.yamlconda activate neuralangelo

For COLMAP, alternative installation options are also available on theCOLMAP website.

Please refer toData Preparation for step-by-step instructions.
We assume known camera poses for each extracted frame from the video.The code uses the same json format asInstant NGP.

EXPERIMENT=toy_exampleGROUP=example_groupNAME=example_nameCONFIG=projects/neuralangelo/configs/custom/${EXPERIMENT}.yamlGPUS=1# use >1 for multi-GPU training!torchrun --nproc_per_node=${GPUS} train.py \    --logdir=logs/${GROUP}/${NAME} \    --config=${CONFIG} \    --show_pbar

Some useful notes:

• This codebase supports logging withWeights & Biases. You should have a W&B account for this.
  • Add--wandb to the command line argument to enable W&B logging.
  • Add--wandb_name to specify the W&B project name.
  • More detailed control can be found in theinit_wandb() function inimaginaire/trainers/base.py.
• Configs can be overridden through the command line (e.g.--optim.params.lr=1e-2).
• Set--checkpoint={CHECKPOINT_PATH} to initialize with a certain checkpoint; set--resume to resume training.
• If appearance embeddings are enabled, make suredata.num_images is set to the number of training images.

Use the following command to run isosurface mesh extraction:

CHECKPOINT=logs/${GROUP}/${NAME}/xxx.ptOUTPUT_MESH=xxx.plyCONFIG=logs/${GROUP}/${NAME}/config.yamlRESOLUTION=2048BLOCK_RES=128GPUS=1# use >1 for multi-GPU mesh extractiontorchrun --nproc_per_node=${GPUS} projects/neuralangelo/scripts/extract_mesh.py \    --config=${CONFIG} \    --checkpoint=${CHECKPOINT} \    --output_file=${OUTPUT_MESH} \    --resolution=${RESOLUTION} \    --block_res=${BLOCK_RES}

Some useful notes:

• Add--textured to extract meshes with textures.
• Add--keep_lcc to remove noises. May also remove thin structures.
• LowerBLOCK_RES to reduce GPU memory usage.
• LowerRESOLUTION to reduce mesh size.

1. Q: CUDA out of memory. How do I decrease the memory footprint?
   A: Neuralangelo requires at least 24GB GPU memory with our default configuration. If you run out of memory, consider adjusting the following hyperparameters undermodel.object.sdf.encoding.hashgrid (with suggested values):

   GPU VRAM	Hyperparameter
   8GB	dict_size=20,dim=4
   12GB	dict_size=21,dim=4
   16GB	dict_size=21,dim=8

   Please note that the above hyperparameter adjustment may sacrifice the reconstruction quality.

   If Neuralangelo runs fine during training but CUDA out of memory during evaluation, consider adjusting the evaluation parameters underdata.val, including setting smallerimage_size (e.g., maximum resolution 200x200), and settingbatch_size=1,subset=1.

2. Q: The reconstruction of my custom dataset is bad. What can I do?
   A: It is worth looking into the following:

   • The camera poses recovered by COLMAP may be off. We have implemented tools (usingBlender orJupyter notebook) to inspect the COLMAP results.
   • The computed bounding regions may be off and/or too small/large. Please refer todata preprocessing on how to adjust the bounding regions manually.
   • The video capture sequence may contain significant motion blur or out-of-focus frames. Higher shutter speed (reducing motion blur) and smaller aperture (increasing focus range) are very helpful.

If you find our code useful for your research, please cite

@inproceedings{li2023neuralangelo,  title={Neuralangelo: High-Fidelity Neural Surface Reconstruction},  author={Li, Zhaoshuo and M\"uller, Thomas and Evans, Alex and Taylor, Russell H and Unberath, Mathias and Liu, Ming-Yu and Lin, Chen-Hsuan},  booktitle={IEEE Conference on Computer Vision and Pattern Recognition ({CVPR})},  year={2023}}