百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
4

4K-NeRF

> 编程语言
开源

官方实现 arxiv 论文 "4K-NeRF: 高保真度的神经辐射场在超高分辨率下"

386 stars0 点赞0 次浏览
访问官网GitHub

工具介绍

官方实现 arxiv 论文 "4K-NeRF: 高保真度的神经辐射场在超高分辨率下"

4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions

Zhongshu Wang, Lingzhi Li, Zhen Shen, Li Shen, Liefeng Bo

Alibaba Group

[Project Webpage] [Bibtex]

4K-Results

Due to the limitation of video size displayed on the webpage, the following videos are down-sampled. For the original 4K video comparison, please check under the 4K_results folder.

https://user-images.githubusercontent.com/15401551/206893466-7bb285f7-67e4-42b5-9fa9-d3e9e784c197.mp4

https://user-images.githubusercontent.com/15401551/206893643-a4c09b2b-fb7b-4af9-aa4c-8acf006f4e07.mp4

Setup

Dependencies

bash
pip install -r requirements.txt

Pytorch and torch_scatter installation is machine dependent, please install the correct version for your machine.

Datasets

nerf_llff_data is the mainly used dataset as it is the only dataset that has 4K resolution images.

nerf_synthetic was used in some ablation studys.

Put them in the ./datasets sub-folder.

Pre Trained Model

We partially initialize VC-Decoder with a pretrained model to speedup convergence. Put the downloaded pretrained weight in ./pretrained sub-folder. Note that 4K-NeRF can be trained without pretrained weights.

Directory-structure:

4K-NeRF
│ 
│
├──pretrained
│   └──RealESRNet_x4plus.pth
│ 
│ 
└── datasets
    ├── nerf_synthetic     # Link: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
    │   └── [chair|drums|ficus|hotdog|lego|materials|mic|ship]
    │       ├── [train|val|test]
    │       │   └── r_*.png
    │       └── transforms_[train|val|test].json
    │
    │
    └── nerf_llff_data     # Link: https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
        └── [fern|flower|fortress|horns|leaves|orchids|room|trex]

Training

Our method can train from scratch for any given scene, but we recommend pre-train the VC-Encoder for faster convergence:

LLFF: python run.py --config configs/llff/fern_lg_pretrain.py --render_test

NeRF_Synthetic: python run.py --config configs/syn/syn_default.py --render_test

After the pre-training, we use following commands to train the full 4K-NeRF with different configs:

  • traing 4K resolution with L1 loss:

    bash
    python run_sr.py --config configs/llff/fern_lg_joint_l1.py \
           --render_test --ftdv_path logs/llff/pretrain_fern_l1/fine_last.tar \
           --ftsr_path ./pretrained/RealESRNet_x4plus.pth --test_tile 510
  • traing 4K resolution with L1+GAN loss:

    bash
    python run_sr.py --config configs/llff/fern_lg_joint_l1+gan.py \
            --render_test --ftdv_path logs/llff/pretrain_fern_l1/fine_last.tar \
            --ftsr_path ./pretrained/RealESRNet_x4plus.pth --test_tile 510
  • traing 1K resolution (LLFF) with L1+GAN loss:

    bash
    python run_sr.py --config configs/llff/1x_fern_lg_joint_l1+gan.py \
            --render_test --ftdv_path logs/llff/pretrain_fern_l1/fine_last.tar \
            --ftsr_path ./pretrained/RealESRNet_x4plus.pth 
  • traing 1K resolution (NeRF_Synthetic) with L1+GAN loss:

    bash
    python run_sr.py --config configs/syn/1x_chair_joint_l1+gan.py \
             --render_test --ftdvcoa_path ./logs/syn/pretrain_chair/coarse_last.tar \
             --ftdv_path ./logs/syn/pretrain_chair/fine_last.tar \
             --ftsr_path ./pretrained/RealESRNet_x4plus.pth 

Evaluation

Evaluate at 4K resolution:

bash
python run_sr.py --config configs/fern_lg_joint_l1+gan.py \
        --render_test --render_only --dv_path logs/llff//render_val/lpips_dvgo.tar \
        --sr_path logs/llff//render_val/sresrnet_latest.pth --test_tile 510

Replace the `` to the corresponding experiment name.

Reference

  • Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
  • BasicSR: Open Source Image and Video Restoration Toolbox

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言