Skip to content

DATASETS.md

Latest commit

 

History

History
40 lines (30 loc) · 1.76 KB

DATASETS.md

File metadata and controls

40 lines (30 loc) · 1.76 KB

Datasets

Training datasets

For training, we mainly use RealEstate10K, and ACID datasets. We provide the data processing scripts to convert the original datasets to pytorch chunk files which can be directly loaded with this codebase.

Expected folder structure:

├── datasets
│   ├── re10k
│   ├── ├── train
│   ├── ├── ├── 000000.torch
│   ├── ├── ├── ...
│   ├── ├── ├── index.json
│   ├── ├── test
│   ├── ├── ├── 000000.torch
│   ├── ├── ├── ...
│   ├── ├── ├── index.json
│   ├── acid
│   ├── ├── train
│   ├── ├── ├── 000000.torch
│   ├── ├── ├── ...
│   ├── ├── ├── index.json
│   ├── ├── test
│   ├── ├── ├── 000000.torch
│   ├── ├── ├── ...
│   ├── ├── ├── index.json

By default, we assume the datasets are placed in datasets/re10k, and datasets/acid. Otherwise you will need to specify your dataset path with dataset.DATASET_NAME.roots=[YOUR_DATASET_PATH] in the running script.

We also provide instructions to convert additional datasets to the desired format.

RealEstate10K and ACID

For experiments on RealEstate10K, we primarily follow pixelSplat and MVSplat to train and evaluate on 256x256 resolution.

Please refer to here for acquiring the processed 360p dataset (360x640 resolution).