datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
annotated-3DGS-artifacts
Puzzle Similarity
Project page | Paper | Code
This repository contains the dataset presented in the ICCV 2025 paper "Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions"Authors: Nicolai Hermann, Jorge Condor, and Piotr Didyk
Dataset Description
The Dataset consists of 36 hand-selected 3D Gaussian Splatting renderings containing common reconstruction artefacts, (aligned) ground truths, human-annotated… See the full description on the dataset page: https://huggingface.co/datasets/nihermann/annotated-3DGS-artifacts.3dgs-assets3dgs-mipneft360-images23DGS_Tamper3dgs_cldm_dataset_and_weight3dgs-benchmarkcrowd-3dgs
🧑🤝🧑 Crowd-3DGS Dataset
A sequential-frame dataset of a real-world crowd protest scene, fully prepared for 3D Gaussian Splatting (3DGS) reconstruction — including high- and low-resolution image sets, COLMAP sparse reconstruction, stereo depth maps, and ready-to-run COLMAP scripts.
Dataset Description
Crowd-3DGS is a single-scene video-derived dataset capturing a crowd protest, intended for 3D scene reconstruction and novel view synthesis using 3D Gaussian… See the full description on the dataset page: https://huggingface.co/datasets/siyah1/crowd-3dgs.Poison-3DGS
Poison-3DGS (review copy)
Anonymous data release accompanying a paper under double-blind review.
For review purposes only. Please do not redistribute it or use it for any other purpose.
This review set contains 150 scenes (125 poisoned and 25 clean), built from 25 base scenes. The full
benchmark of 1,353 scenes (1,253 poisoned and 100 clean) will be released after acceptance. The release
contains poisoned training data and manipulated 3D Gaussian Splatting models.… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-user-submission/Poison-3DGS.VR27_3DGS_DataSet
VR27 Real-Scene 3DGS Collection
本集合包含 12 个经人工筛选的真实场景。每个场景统一提供:
scenes/<scene>/
├── images/
├── sparse/0/
│ ├── cameras.bin
│ ├── images.bin
│ └── points3D.bin
├── 3dgs/
│ └── point_cloud.ply
├── overview.jpg
└── metadata.json
数据处理统一表述为:
真实多视角 RGB → 图像筛选/去畸变 → COLMAP/SfM → 标准 3DGS →
必要时 LightGaussian Prune & Recovery → 结构校验与 VR 质量/性能验证。
数据来源与许可
Room、Garden:Mip-NeRF 360;模型来自 Graphdeco 官方 3DGS 发布。
Playroom:Deep Blending;模型来自 Graphdeco 官方 3DGS 发布。… See the full description on the dataset page: https://huggingface.co/datasets/warmstones/VR27_3DGS_DataSet.so101_3dgs_pick_place_v1This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 30,
"features": {
"observation.state": {
"dtype": "float32",
"shape": [
6
],
"names": [
"shoulder_pan",
"shoulder_lift",
"elbow_flex",
"wrist_flex",
"wrist_roll",
"gripper"
]… See the full description on the dataset page: https://huggingface.co/datasets/zzanu31/so101_3dgs_pick_place_v1.3DGS-Testing3dgs3DGS-CD-processed3DGS-binary-segmentation3dgsl3DGS_datasets
3DGS Dataset Collection
This repository provides a collection of 10 scenes for 3D Gaussian Splatting (3DGS) research.The scenes are collected from several popular datasets, including Instruct-NeRF2NeRF, Mip-NeRF 360, BlendedMVS, and DreamEditor.
We sincerely thank the authors of these excellent works for making their datasets and resources publicly available.
Included Scenes
The dataset contains the following 10 scenes:
face
bear
person
bonsai
garden
Stone horse… See the full description on the dataset page: https://huggingface.co/datasets/yuhaiyang123/3DGS_datasets.chair-source-images-3DGS3dgs-ue3DGS_sample_scenes
KU-VR-Lab Datasets
KU-VR-Lab에서 공개하는 3D Vision / Graphics 연구·실습용 데이터셋 모음.
Datasets
3D Gaussian Splatting 학습/실습용 샘플 장면.
Name
Images
Resolution
Description
cashew
50
1600px
캐슈너트 봉지 360° 회전 촬영
License
모든 데이터셋은 CC BY 4.0 라이선스로 배포됩니다.
VR27_3DGS3DGS_datasets
3DGS Dataset Collection
This repository provides a collection of 10 scenes for 3D Gaussian Splatting (3DGS) research.The scenes are collected from several popular datasets, including Instruct-NeRF2NeRF, Mip-NeRF 360, BlendedMVS, and DreamEditor.
We sincerely thank the authors of these excellent works for making their datasets and resources publicly available.
Included Scenes
The dataset contains the following 10 scenes:
face
bear
person
bonsai
garden
Stone horse… See the full description on the dataset page: https://huggingface.co/datasets/zephyr663/3DGS_datasets.RWAVS_3DGSconformal-uncertainty-3dgs
Output Folder Structure
The output/ folder contains everything needed to reproduce analysis results without rerunning training, rendering, or conformal prediction.
High-Level Layout
output/
<scene_name>/
splits/
train.txt
calib.txt
test.txt
summary.txt
cfg_args
cameras.json
exposure.json # if present
input.ply # if present
point_cloud/
iteration_<N>/… See the full description on the dataset page: https://huggingface.co/datasets/nbhagat/conformal-uncertainty-3dgs.Ortho-3DGS-Datasets
