datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
nerf-synthetic-mirrornerf-gs-datasetsI keep a collection compiled of existing datasets from various sources for training NeRFs or Splats. This dataset is most of that collection. All of the individual scenes also have a trained Gaussian Splat.
https://rishit-dagli.github.io/2025/03/28/nerf-gs-datasets.html
bad_prompt
Negative Embedding / Textual Inversion
Idea
The idea behind this embedding was to somehow train the negative prompt as an embedding, thus unifying the basis of the negative prompt into one word or embedding.
Side note: Embedding has proven to be very helpful for the generation of hands! :)
Usage
To use this embedding you have to download the file aswell as drop it into the "\stable-diffusion-webui\embeddings" folder.
Please put the embedding in… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/bad_prompt.Mip-NeRF360nerfbaselines-datanerf-syntheticdatasetsnerf-syntheticnerf_syntheticnerfbaselines-supplementaryrobust-e-nerf
Robust e-NeRF Synthetic Event Dataset
This repository contains the synthetic event dataset used in Robust e-NeRF to study the collective effect of camera speed profile, contrast threshold variation and refractory period on the quality of NeRF reconstruction from a moving event camera. The dataset is simulated using an improved version of ESIM with three different camera configurations of increasing difficulty levels (i.e. easy, medium and hard)… See the full description on the dataset page: https://huggingface.co/datasets/wengflow/robust-e-nerf.deblur-e-nerf
Deblur e-NeRF Synthetic Event Dataset
This repository contains the synthetic event dataset used in Deblur e-NeRF to study the collective effect of camera speed and scene illuminance on the quality of NeRF reconstruction from a moving event camera. It is an extension of the synthetic event dataset used in Robust e-NeRF. The dataset is simulated using an improved version of ESIM with three different camera configurations of increasing difficulty… See the full description on the dataset page: https://huggingface.co/datasets/wengflow/deblur-e-nerf.great-e-nerfsqueeze3d_rf_nerfmaeThis dataset is for the paper Squeeze3D: Extreme Neural Compression with Latent Space Bridging (TMLR 2026). It contains latent representations of 3D data used for training and evaluating the Squeeze3D model.
Paper
Project page
Code
Citation
@article{dagli2026squeeze3d,
title={Squeeze3D: Extreme Neural Compression with Latent Space Bridging},
author={Rishit Dagli and Yushi Guan and Sankeerth Durvasula and Mohammadreza Mofayezi and Nandita Vijaykumar},
journal={Transactions on… See the full description on the dataset page: https://huggingface.co/datasets/rishitdagli/squeeze3d_rf_nerfmae.HSI-SC-NeRF
HSI-SC-NeRF: NeRF-based Hyperspectral 3D Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset accompanies our work on HSI-SC-NeRF, a stationary-camera-based hyperspectral NeRF framework for 3D plant phenotyping and postharvest agricultural inspection. Unlike conventional NeRF pipelines that require camera motion around a static object, our approach uses a fixed camera and a rotating object, making the… See the full description on the dataset page: https://huggingface.co/datasets/Smaraharamrita/HSI-SC-NeRF.HSI-SC-NeRF
HSI-SC-NeRF: NeRF-based Hyperspectral 3D Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset accompanies our work on HSI-SC-NeRF, a stationary-camera-based hyperspectral NeRF framework for 3D plant phenotyping and postharvest agricultural inspection. Unlike conventional NeRF pipelines that require camera motion around a static object, our approach uses a fixed camera and a rotating object, making the acquisition… See the full description on the dataset page: https://huggingface.co/datasets/BGLab/HSI-SC-NeRF.nerfshift-ocr-datasetUnMix-NeRF-ArtifactsSC-NeRF
SC-NeRF: NeRF-based Point Cloud Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset complements our paper on a stationary-camera-based NeRF framework for high-throughput 3D plant phenotyping. Traditional NeRF pipelines require a moving camera around a static object, which is impractical in automated indoor phenotyping environments. Our method enables 3D point cloud (PCD) reconstruction using a stationary… See the full description on the dataset page: https://huggingface.co/datasets/liss222433434/SC-NeRF.sakimi-chan_LoRA
Sakimi-chan LoRA
Who is Sakimi-chan?
Sakimi-chan is a Canadian artist best known for her digital paintings and unique style. She mainly draws fanart of games and popular characters and creates gifs for her fans with voiceovers.
Patreon: https://www.patreon.com/sakimichan
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token:… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/sakimi-chan_LoRA.FSCM_Flood_nerfrobust-e-nerf
Robust e-NeRF Synthetic Event Dataset
This repository contains the synthetic event dataset used in Robust e-NeRF to study the collective effect of camera speed profile, contrast threshold variation and refractory period on the quality of NeRF reconstruction from a moving event camera. The dataset is simulated using an improved version of ESIM with three different camera configurations of increasing difficulty levels (i.e. easy, medium and hard)… See the full description on the dataset page: https://huggingface.co/datasets/gaojz/robust-e-nerf.mega_nerf_rubble_colmapThis repository redistributes the Rubble dataset released by Mega-NeRF. Their original release uses a different data format, so we reran COLMAP and provide a COLMAP-compatible version of Rubble here.
Please cite the original Mega-NeRF paper if you use this dataset:
@InProceedings{Turki_2022_CVPR,
author = {Turki, Haithem and Ramanan, Deva and Satyanarayanan, Mahadev},
title = {Mega-NERF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs}… See the full description on the dataset page: https://huggingface.co/datasets/HexuZhao/mega_nerf_rubble_colmap.NeRF_RPNJohn_Kafka_LoRA
John Kafka Artstyle LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use these strength with the assosiated model:
Soft-Version:
0.85-1 for AbyssOrangeMix2
0.75-0.9 for Kenshi… See the full description on the dataset page: https://huggingface.co/datasets/Nerfgun3/John_Kafka_LoRA.SC-NeRF
SC-NeRF: NeRF-based Point Cloud Reconstruction using a Stationary Camera for Agricultural Applications
📄 Paper Link
🧾 Overview
This dataset complements our paper on a stationary-camera-based NeRF framework for high-throughput 3D plant phenotyping. Traditional NeRF pipelines require a moving camera around a static object, which is impractical in automated indoor phenotyping environments. Our method enables 3D point cloud (PCD) reconstruction using a stationary camera and… See the full description on the dataset page: https://huggingface.co/datasets/BGLab/SC-NeRF.Explicit-NeRF-QAIf you use our dataset, please cite the following article:
@article{xing2024explicit,
title={Explicit-NeRF-QA: A quality assessment database for explicit NeRF model compression},
author={Xing, Yuke and Yang, Qi and Yang, Kaifa and Xu, Yilin and Li, Zhu},
journal={arXiv preprint arXiv:2407.08165},
year={2024}
}
sonic-nerf
Sonic NeRF
Sample data for a synthetic NeRF pipeline I'm working on. This repository is a temporary backup. I will delete it sometime in the future.
NeRF Dataset
The dataset for training a NeRF can be found in the multi_view_renders folder.
The multi_view_renders/transforms.json file contains a record of the half FOV in radians as well as camera poses for each frame.
The camera poses are given as column-major affine transformation matrices.
Mip-NeRF_360_Processed_with_Nerfstudio