datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
IPL-Cityscapes-Illuminants
IPL-CityscapesIlluminants-dataset
Illuminant modified dataset version of the famous autonomous driving semantic segmentation Cityscapes dataset.
Dataset generation
For each image, we generate a flat (constant) light spectrum and compute the pixel reflectances that obtain the RGM pixel values. Once we have the pixel reflectances, we generate different light spectrums of different dominant wavelengths (colors) and saturations and compute the new modified images. We apply… See the full description on the dataset page: https://huggingface.co/datasets/isp-uv-es/IPL-Cityscapes-Illuminants.cityscapesversion https://git-lfs.github.com/spec/v1
oid sha256:4bcf87ecfbbb8e07a01b21415a970c8b53a5283bf6872b657040d3f45c9241f7
size 31
IPL-Cityscapes-LuminanceContrasts
IPL-CityscapesLuminanceContrasts-dataset
Controled luminance and contrasts modified dataset version of the famous autonomous driving semantic segmentation Cityscapes dataset.
Dataset generation
For each original image, we convert it to ATD color space. Once in this space, we compute its mean luminance, achromatic contrast and chromatic contast. We modify each of its characteristics in turns from 0.5 to 1.5 of its original value. Then we return the image to RGB space. We… See the full description on the dataset page: https://huggingface.co/datasets/isp-uv-es/IPL-Cityscapes-LuminanceContrasts.TTA-Cityscapes-Ccityscapescityscapes_segmentationfloorplans-cityscapes
Dataset Summary
This is a curated collection of floorplan images sourced from across the internet. It is intended for research in architectural AI, layout generation, and urban scene understanding.
Data format: Image files with associated integer labels.
Sources: Publicly available images from various web sources (This dataset is one unified collections).
Purpose: Educational and research use.
Dataset Structure
The dataset follows the standard Hugging Face Image… See the full description on the dataset page: https://huggingface.co/datasets/wheres-my-python/floorplans-cityscapes.CityscapesCityscapes_Style_2048_1024CityScapescityscapes_sequence_1024by512CityScapes-LabelCityscapes_M3FDThis repository contains the inference results on the CityScapes dataset. The model weights used for this inference were obtained by training on the M3FD dataset, utilizing the official training configuration provided by F-ViTA.
cityscapes-pseudo-labels
Cityscapes Unsupervised Panoptic Pseudo-Labels
Pseudo-labels for unsupervised panoptic segmentation on Cityscapes, generated using overclustered k-means semantics + depth-guided instance splitting.
Contents
Pseudo-Labels
Directory
Description
Files
Format
pseudo_semantic_raw_k80/
Overclustered k=80 semantic labels
~3.5K PNGs + centroids.npz
PNG (values 0-79), train/val split
cups_pseudo_labels_depthpro_tau020/
CUPS-format combined labels (DepthPro… See the full description on the dataset page: https://huggingface.co/datasets/qbit-glitch/cityscapes-pseudo-labels.Cityscapes_KAISTv2This is the result obtained by inference on the Cityscapes dataset using the KAIST weights provided by the official F-ViTA documentation (resolution 512).
synthia-rand-cityscapes-16class-parquet
SYNTHIA-RAND-CITYSCAPES 16-class Parquet
Converted from the original SYNTHIA-RAND-CITYSCAPES release.
Notes
image: RGB image bytes
label: PNG bytes of remapped segmentation mask
Label train IDs are in [0..15]
Ignore label is 255
label_format: synthia_to_cityscapes16_trainid
sim2real_gta5_to_cityscapescityscapesCityscapesinstructPix2Pix_cityscapes_512cityscapes-pairedCityscapes-BSRcityscapes_valIPL-Cityscapes-Grayscale-Illuminants
IPL-Cityscapes-Grayscale-Illuminants dataset
Illuminant modified dataset version of the grayscale famous autonomous driving semantic segmentation Cityscapes dataset.
Dataset generation
For each image, we first convert it to grayscale. Then, we generate a flat (constant) light spectrum and compute the pixel reflectances that obtain the RGM pixel values. Once we have the pixel reflectances, we generate different light spectrums of different dominant wavelengths (colors) and… See the full description on the dataset page: https://huggingface.co/datasets/isp-uv-es/IPL-Cityscapes-Grayscale-Illuminants.cityscapes_eomtcityscapesCaptioned_CityscapesCaptioned by caption_coco_opt6.7b
controlnet-cityscapes
Dataset Card for Dataset Name
Extract Cityscapes dataset (https://www.cityscapes-dataset.com/) training images and their semantic maps. Captions are generated with the pre-trained BLIP-large model. Please refer to the license session in Cityscapes if you would like to use the dataset.
Dataset Details
2975 training images and its semantic maps with auto-generated captions.
DSIC-Cityscapes_dataThis is the Cityscapes dataset used to train the models in the GitHub repository https://github.com/abilalk02/D-SIC. The original complete dataset can be found here: https://www.cityscapes-dataset.com/.
The train and test datasets should be downloaded and saved as .tar files in the 'data/train/without_captions' and 'data/test/without_captions' folders in the GitHub repository respectively. D-SIC is trained without text caption conditioning. Thus, the .txt files are empty.
Cityscapes