Shadowgraph
About
Sign in

johnnylu305/DF3DV

[ECCV 2026] DF3DV-1K Dataset and DI²FIX Codebase

42

stars

68

commits

Python

primary language

Aug 21, 2026

updated

README

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

Cheng-You Lu1†, Yi-Shan Hung2†, Wei-Ling Chi3*, Hao-Ping Wang3*, Charlie Li-Ting Tsai1*, Yu-Cheng Chang1, Yu-Lun Liu3, Thomas Do1, Chin-Teng Lin1

1University of Technology Sydney   2University of Sydney  3National Yang Ming Chiao Tung University  
†Equal Contribution  
*Equal Contribution  

Project Page · Paper · DF3DV-1K Dataset · DF3DV Benchmark

DI²FIX Dataset · DI²FIX Demo Page · DI²FIX Codebase · DI²FIX Checkpoint

✨ News

  • DF3DV-Extra is now available, adding more than 1,000 new scenes and doubling the size of the DF3DV dataset! Please temporarily assign the credit for the DF3DV-Extra dataset to the DF3DV-1K team by mentioning that your work uses DF3DV-Extra, collected by the DF3DV-1K group, if you find the dataset useful.

Introduction

DF3DV-1K Introduction

Outline

DF3DV-1K

We release one thousand scenes with clean and cluttered images for distractor-free 3D vision research. The first few chunks were captured using interval shooting, resulting in a more casual and lower-quality capture setting (e.g., 0000 vs. 0024).

Directory Structure

Example Directory Structure 
├── DF3DV-1K-Star
│   ├── 0000
│   │   ├── 040625-LundoBin
│   │   │   ├── 040625-LundoBin-All (curated data)
│   │   │   │   ├── images (COLMAP input images)
│   │   │   │   │   ├── clutter_IMG_7042.JPG 
│   │   │   │   │   ├── ...
│   │   │   │   │   └── extra_IMG_7041.JPG
│   │   │   │   ├── sparse (COLMAP result)
│   │   │   │   │   └── 0
│   │   │   │   │       ├── cameras.bin
│   │   │   │   │       ├── images.bin
│   │   │   │   │       ├── points3D.bin
│   │   │   │   │       └── project.ini
│   │   │   │   ├── split.json (list of clean and cluttered images)
│   │   │   │   ├── transforms_clutter.json (Instant-NGP JSON file for cluttered images only)
│   │   │   │   ├── transforms_extra.json (Instant-NGP JSON file for clean images only)
│   │   │   │   ├── transforms.json (Instant-NGP JSON file for all images)
│   │   │   │   ├── undistortion_images (COLMAP-undistorted images)
│   │   │   │   │   ├── clutter_IMG_7042.JPG
│   │   │   │   │   ├── ...
│   │   │   │   │   └── extra_IMG_7041.JPG
│   │   │   │   └── undistortion_sparse (COLMAP-undistorted result)
│   │   │   │       └── 0
│   │   │   │           ├── cameras.bin
│   │   │   │           ├── cameras.txt
│   │   │   │           ├── images.bin
│   │   │   │           ├── images.txt
│   │   │   │           ├── points3D.bin
│   │   │   │           └── points3D.txt
│   │   │   ├── 040625-LundoBin-Clean (candidate clean images)
│   │   │   │   └── images
│   │   │   │       ├── IMG_6957.JPG
│   │   │   │       ├── ...
│   │   │   │       └── IMG_7041.JPG
│   │   │   └── 040625-LundoBin-Clutter (candidate cluttered images)
│   │   │       └── images
│   │   │            ├── IMG_7042.JPG
│   │   │            ├── ...
│   │   │            └── IMG_7140.JPG
│   │   ├── ...
│   │   └── 090625-BlueBikeBell
│   ├── ...
│   └── 0024
└── DF3DV-41
    ├── 021125-Chess
    │   ├── 021125-Chess-All
    │   │   ├── images
    │   │   ├── sparse
    │   │   │   └── 0
    │   │   ├── undistortion_images
    │   │   └── undistortion_sparse
    │   │       └── 0
    │   ├── 021125-Chess-Clean
    │   │   └── images
    │   └── 021125-Chess-Clutter
    │       └── images
    ├── ...
    └── 301025-TempleDrumIncense

Download

The masked dataset can be downloaded from both Hugging Face and Google Cloud.

The original dataset can be downloaded from both Hugging Face and Google Cloud after completing the form and agreeing to the terms of use here.

DF3DV-1K-Fixer

We also release paired 3DGS/Distractor-Free 3DGS renderings and corresponding ground-truth images for distractor-removal and fixer research.

Directory Structure

Example Directory Structure 
├── Train
│   └── DF3DV-1K-Star-Fixer
│       ├── 0000
│       │   ├── 040625-LundoBin
│       │   │   └── 040625-LundoBin-All
│       │   │       ├── MODELS
│       │   │       │   ├── 3DGS (rendering results and ground-truth images)
│       │   │       │   │   ├── 040625-LundoBin_3DGS_extra_IMG_6957_source.png
│       │   │       │   │   ├── ...
|       |   │       │   │   └── 040625-LundoBin_3DGS_extra_IMG_7041_target.png
│       │   │       │   ├── ...
│       │   │       │   └── WILDGS
│       │   │       ├── NN (nearest neighbors for images)
|       |   |       │   └── nn_rank_by_name.json
│       │   │       └── undistortion_sparse (COLMAP result)
│       │   │           └── 0
│       │   │               ├── cameras.bin
│       │   │               ├── cameras.txt
│       │   │               ├── images.bin
│       │   │               ├── images.txt
│       │   │               ├── points3D.bin
│       │   │               ├── points3D.ply
│       │   │               └── points3D.txt
│       │   ├── ...
│       │   └── 090625-BlueBikeBell
│       ├── ...
│       └── 0024
└── Val
    ├── DF3DV-41-Fixer
    │   ├── 021125-Chess
    │   │   └── 021125-Chess-All
    │   │       ├── MODELS
    │   │       │   ├── 3DGS
    │   │       │   ├── ...
    │   │       │   └── WILDGS
    │   │       ├── NN
    │   │       └── undistortion_sparse
    │   │           └── 0
    │   ├── ...   
    │   └── 301025-TempleDrumIncense
    └── on-the-go
        ├── corner
        │   └── corner-All
        │       ├── MODELS
        │       │   ├── 3DGS
        │       │   ├── ...
        │       │   └── WILDGS
        │       ├── NN
        │       └── undistortion_sparse
        │           └── 0
        ├── ...
        └── spot

Download

The masked dataset can be downloaded from both Hugging Face and Google Cloud.

The original dataset can be downloaded from both Hugging Face and Google Cloud after completing the form and agreeing to the terms of use here.

Citation

@article{lu2026df3dv,
  title={DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis},
  author={Lu, Cheng-You and Hung, Yi-Shan and Chi, Wei-Ling and Wang, Hao-Ping and Tsai, Charlie Li-Ting and Chang, Yu-Cheng and Liu, Yu-Lun and Do, Thomas and Lin, Chin-Teng},
  journal={arXiv preprint arXiv:2604.13416},
  year={2026}
}

Contributors

johnnylu305

68 commits

Similar repos

ChengYou305/DF3DV-1K

Dataset

2

ChengYou305/DF3DV-1K-Fixer

Dataset

0

ChengYou305/DF3DV-Extra

Dataset

0

ChengYou305/DF3DV-Extra-Fixer

Dataset

0

Eyeline-Labs/Vista4D-Eval-Data

Dataset

3

kairunwen/InstantSplat

Dataset

5

ChengYou305/DI2FIX_HF

Model

0

sv-pp/SceneVersepp

Official implementation of CVPR26 paper "Lifting Unlabeled Internet-level Data for 3D Scene…

55

Languages

Python

98.0%

Shell

2.0%

johnnylu305/DF3DV

[ECCV 2026] DF3DV-1K Dataset and DI²FIX Codebase

42

stars

68

commits

Python

primary language

Aug 21, 2026

updated

README

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

Cheng-You Lu1†, Yi-Shan Hung2†, Wei-Ling Chi3*, Hao-Ping Wang3*, Charlie Li-Ting Tsai1*, Yu-Cheng Chang1, Yu-Lun Liu3, Thomas Do1, Chin-Teng Lin1

1University of Technology Sydney   2University of Sydney  3National Yang Ming Chiao Tung University  
†Equal Contribution  
*Equal Contribution  

Project Page · Paper · DF3DV-1K Dataset · DF3DV Benchmark

DI²FIX Dataset · DI²FIX Demo Page · DI²FIX Codebase · DI²FIX Checkpoint

✨ News

  • DF3DV-Extra is now available, adding more than 1,000 new scenes and doubling the size of the DF3DV dataset! Please temporarily assign the credit for the DF3DV-Extra dataset to the DF3DV-1K team by mentioning that your work uses DF3DV-Extra, collected by the DF3DV-1K group, if you find the dataset useful.

Introduction

DF3DV-1K Introduction

Outline

DF3DV-1K

We release one thousand scenes with clean and cluttered images for distractor-free 3D vision research. The first few chunks were captured using interval shooting, resulting in a more casual and lower-quality capture setting (e.g., 0000 vs. 0024).

Directory Structure

Example Directory Structure 
├── DF3DV-1K-Star
│   ├── 0000
│   │   ├── 040625-LundoBin
│   │   │   ├── 040625-LundoBin-All (curated data)
│   │   │   │   ├── images (COLMAP input images)
│   │   │   │   │   ├── clutter_IMG_7042.JPG 
│   │   │   │   │   ├── ...
│   │   │   │   │   └── extra_IMG_7041.JPG
│   │   │   │   ├── sparse (COLMAP result)
│   │   │   │   │   └── 0
│   │   │   │   │       ├── cameras.bin
│   │   │   │   │       ├── images.bin
│   │   │   │   │       ├── points3D.bin
│   │   │   │   │       └── project.ini
│   │   │   │   ├── split.json (list of clean and cluttered images)
│   │   │   │   ├── transforms_clutter.json (Instant-NGP JSON file for cluttered images only)
│   │   │   │   ├── transforms_extra.json (Instant-NGP JSON file for clean images only)
│   │   │   │   ├── transforms.json (Instant-NGP JSON file for all images)
│   │   │   │   ├── undistortion_images (COLMAP-undistorted images)
│   │   │   │   │   ├── clutter_IMG_7042.JPG
│   │   │   │   │   ├── ...
│   │   │   │   │   └── extra_IMG_7041.JPG
│   │   │   │   └── undistortion_sparse (COLMAP-undistorted result)
│   │   │   │       └── 0
│   │   │   │           ├── cameras.bin
│   │   │   │           ├── cameras.txt
│   │   │   │           ├── images.bin
│   │   │   │           ├── images.txt
│   │   │   │           ├── points3D.bin
│   │   │   │           └── points3D.txt
│   │   │   ├── 040625-LundoBin-Clean (candidate clean images)
│   │   │   │   └── images
│   │   │   │       ├── IMG_6957.JPG
│   │   │   │       ├── ...
│   │   │   │       └── IMG_7041.JPG
│   │   │   └── 040625-LundoBin-Clutter (candidate cluttered images)
│   │   │       └── images
│   │   │            ├── IMG_7042.JPG
│   │   │            ├── ...
│   │   │            └── IMG_7140.JPG
│   │   ├── ...
│   │   └── 090625-BlueBikeBell
│   ├── ...
│   └── 0024
└── DF3DV-41
    ├── 021125-Chess
    │   ├── 021125-Chess-All
    │   │   ├── images
    │   │   ├── sparse
    │   │   │   └── 0
    │   │   ├── undistortion_images
    │   │   └── undistortion_sparse
    │   │       └── 0
    │   ├── 021125-Chess-Clean
    │   │   └── images
    │   └── 021125-Chess-Clutter
    │       └── images
    ├── ...
    └── 301025-TempleDrumIncense

Download

The masked dataset can be downloaded from both Hugging Face and Google Cloud.

The original dataset can be downloaded from both Hugging Face and Google Cloud after completing the form and agreeing to the terms of use here.

DF3DV-1K-Fixer

We also release paired 3DGS/Distractor-Free 3DGS renderings and corresponding ground-truth images for distractor-removal and fixer research.

Directory Structure

Example Directory Structure 
├── Train
│   └── DF3DV-1K-Star-Fixer
│       ├── 0000
│       │   ├── 040625-LundoBin
│       │   │   └── 040625-LundoBin-All
│       │   │       ├── MODELS
│       │   │       │   ├── 3DGS (rendering results and ground-truth images)
│       │   │       │   │   ├── 040625-LundoBin_3DGS_extra_IMG_6957_source.png
│       │   │       │   │   ├── ...
|       |   │       │   │   └── 040625-LundoBin_3DGS_extra_IMG_7041_target.png
│       │   │       │   ├── ...
│       │   │       │   └── WILDGS
│       │   │       ├── NN (nearest neighbors for images)
|       |   |       │   └── nn_rank_by_name.json
│       │   │       └── undistortion_sparse (COLMAP result)
│       │   │           └── 0
│       │   │               ├── cameras.bin
│       │   │               ├── cameras.txt
│       │   │               ├── images.bin
│       │   │               ├── images.txt
│       │   │               ├── points3D.bin
│       │   │               ├── points3D.ply
│       │   │               └── points3D.txt
│       │   ├── ...
│       │   └── 090625-BlueBikeBell
│       ├── ...
│       └── 0024
└── Val
    ├── DF3DV-41-Fixer
    │   ├── 021125-Chess
    │   │   └── 021125-Chess-All
    │   │       ├── MODELS
    │   │       │   ├── 3DGS
    │   │       │   ├── ...
    │   │       │   └── WILDGS
    │   │       ├── NN
    │   │       └── undistortion_sparse
    │   │           └── 0
    │   ├── ...   
    │   └── 301025-TempleDrumIncense
    └── on-the-go
        ├── corner
        │   └── corner-All
        │       ├── MODELS
        │       │   ├── 3DGS
        │       │   ├── ...
        │       │   └── WILDGS
        │       ├── NN
        │       └── undistortion_sparse
        │           └── 0
        ├── ...
        └── spot

Download

The masked dataset can be downloaded from both Hugging Face and Google Cloud.

The original dataset can be downloaded from both Hugging Face and Google Cloud after completing the form and agreeing to the terms of use here.

Citation

@article{lu2026df3dv,
  title={DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis},
  author={Lu, Cheng-You and Hung, Yi-Shan and Chi, Wei-Ling and Wang, Hao-Ping and Tsai, Charlie Li-Ting and Chang, Yu-Cheng and Liu, Yu-Lun and Do, Thomas and Lin, Chin-Teng},
  journal={arXiv preprint arXiv:2604.13416},
  year={2026}
}

Similar repos

ChengYou305/DF3DV-1K

Dataset

2

ChengYou305/DF3DV-1K-Fixer

Dataset

0

ChengYou305/DF3DV-Extra

Dataset

0

ChengYou305/DF3DV-Extra-Fixer

Dataset

0

Eyeline-Labs/Vista4D-Eval-Data

Dataset

3

kairunwen/InstantSplat

Dataset

5

ChengYou305/DI2FIX_HF

Model

0

sv-pp/SceneVersepp

Official implementation of CVPR26 paper "Lifting Unlabeled Internet-level Data for 3D Scene…

55

Contributors

johnnylu305

68 commits

Languages

Python

98.0%

Shell

2.0%