Views
No views yet
1pip install torch==2.0.1 torchvision==0.17.2 \
2 numpy pillow matplotlib scipy opencv-pythonrun_any2full.py for single RGBD pairs or batch folders (matched by filename stem).assets/: assets/rgb and assets/depth can be used as inputs, and assets/output shows the corresponding outputs.1# Single pair
2python run_any2full.py \
3 --rgb /path/to/rgb.png \
4 --depth /path/to/depth.png \
5 --checkpoint /path/to/ours_checkpoint.pth \
6 --out_dir ./outputs
7
8# Batch (match by basename)
9python run_any2full.py \
10 --rgb_dir /path/to/rgb_dir \
11 --depth_dir /path/to/depth_dir \
12 --checkpoint /path/to/ours_checkpoint.pth \
13 --out_dir ./outputsutils/denoise.py): Any2Full relies on accurate sparse depth as an anchor, so cleaner raw depth generally yields better results. We provide a simple denoising pre-processing step for convenience.1python run_any2full.py \
2 --rgb /path/to/rgb.png \
3 --depth /path/to/depth.png \
4 --checkpoint /path/to/ours_checkpoint.pth \
5 --out_dir ./outputs \
6 --denoise \
7 --denoise_threshold 2 \
8 --denoise_kernel_size 9--rgb: RGB image path (single mode).--depth: Sparse depth path (.png or .npy) (single mode).--rgb_dir: RGB directory (batch mode, filename stem matched).--depth_dir: Depth directory (batch mode, filename stem matched).--checkpoint: Any2Full checkpoint path (required).--da_ckpt_path: Optional backbone MDE checkpoint (for encoder init).--encoder: Backbone variant (vits, vitb, vitl).--depth_scale: Scale factor for depth PNGs (depth = img / scale).--denoise: Enable sparse depth outlier removal before inference.--denoise_threshold: Outlier threshold (std multiplier).--denoise_kernel_size: Neighborhood size (odd int) for denoise; None auto-estimates.--denoise_min_valid: Minimum valid neighbors for denoise.@article{zhou2026any2full,
title={Any to Full: Prompting Depth Anything for Depth Completion in One Stage},
author={Zhou, Zhiyuan and Liu, Ruofeng and Liu, Taichi and Zuo, Weijian and Wang, Shanshan and Hong, Zhiqing and Zhang, Desheng},
journal={arXiv:2603.05711},
year={2026}
}