深度补全学习笔记

目录

自动驾驶 深度补全

Symphonies

报错'FieldInfo' object has no attribute 'required'

通用深度补全

---

自动驾驶 深度补全

Symphonies

https://github.com/hustvl/Symphonies?tab=readme-ov-file

安装mmcv和mmdet

安装MMCV和MMDET_mmdet.core-CSDN博客

报错'FieldInfo' object has no attribute 'required'

AttributeError: 'FieldInfo' object has no attribute 'required'. Did you mean

AttributeError: ‘FieldInfo‘ object has no attribute ‘required‘. Did you mean: ‘is_required‘?问题解决_fieldinfo' object has no attribute 'required-CSDN博客

通用深度补全

GitHub - ali-vilab/Infusion: Official implementations for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

cd depth_inpainting/run
input_rgb_path=<path to inpainted single image>
input_mask_path=<path to 'mask.png'>
input_depth_path=<path to output folder/train/ours_30000/depth_dis/DSC07956.npy>
c2w=<path to output folder/train/ours_30000/c2w/DSC07956.npy>
intri=<path to output folder/train/ours_30000/intri/DSC07956.npy>
model_path=</path to depth_inpainting model checkpoint>  # absolute path
output_dir=<path to output folder>CUDA_VISIBLE_DEVICES=0 python run_inference_inpainting.py \--input_rgb_path $input_rgb_path \--input_mask $input_mask_path \--input_depth_path $input_depth_path \--model_path $model_path \--output_dir $output_dir \--denoise_steps 20 \--intri $intri \--c2w $c2w \--use_mask\--blend  # Whether to use 'Blended Diffusion (https://arxiv.org/abs/2111.14818)' during inference.