DTU数据集的处理

Posted on Edited on Symbols count in article: 615 Reading time ≈ 1 mins.

gsdsf

sparse view setting

FSGS: real-time few-shot view synthesis using gaussian splatting

https://arxiv.org/pdf/2312.00451

datasets using: NeRF-Synthetic, LLFF, Shiny and Mip-NeRF360 datasets

baselines: DietNeRF [23], RegNeRF [33], FreeNeRF [57], and SparseNeRF， and Mip-NeRF

RegNeRF Training details:

We adhere to the protocol of Yu et al. [62] and evaluate on their reported test set of 15 scenes

For LLFF, we adhere to community standards [36] and use every 8-th image as the held-out test set and select the input views evenly from the remaining images.

mvssplat

https://github.com/donydchen/mvsplat

DTU for testing only

python src/scripts/convert_dtu.py --input_dir PATH_TO_DTU --output_dir datasets/dtu