{"url":"/dataset/freiburg-forest","name":"Freiburg Forest","full_name":"Freiburg Forest","description_markdown":"The **Freiburg Forest** dataset was collected using a Viona autonomous mobile robot platform equipped with cameras for capturing multi-spectral and multi-modal images. The dataset may be used for evaluation of different perception algorithms for segmentation, detection, classification, etc. All scenes were recorded at 20 Hz with a camera resolution of 1024x768 pixels. The data was collected on three different days to have enough variability in lighting conditions as shadows and sun angles play a crucial role in the quality of acquired images. The robot traversed about 4.7 km each day. The dataset creators provide manually annotated pixel-wise ground truth segmentation masks for 6 classes: Obstacle, Trail, Sky, Grass, Vegetation, and Void.\r\n\r\nSource: [http://deepscene.cs.uni-freiburg.de/](http://deepscene.cs.uni-freiburg.de/)\r\nImage Source: [http://deepscene.cs.uni-freiburg.de/](http://deepscene.cs.uni-freiburg.de/)","description_withheld":null,"homepage":"http://deepscene.cs.uni-freiburg.de/","introduced_date":"2021-09-15","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Unsupervised Image-To-Image Translation","url":"/task/unsupervised-image-to-image-translation","datasets_with_task":"/datasets/task/unsupervised-image-to-image-translation"}],"languages":[],"variants":["Freiburg Forest","Freiburg Forest Dataset"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-image-to-image-translation-on-1","task":"Unsupervised Image-To-Image Translation","dataset_variant":"Freiburg Forest Dataset","rows":3,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"In2I","paper":"/paper/in2i-unsupervised-multi-image-to-image","metrics":{"PSNR":"21.65"},"code_links":[{"title":"PramuPerera/In2I","url":"https://github.com/PramuPerera/In2I"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-freiburg-forest","task":"Semantic Segmentation","dataset_variant":"Freiburg Forest","rows":2,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"SSMA","paper":"/paper/self-supervised-model-adaptation-for","metrics":{"Mean IoU":"84.18"},"code_links":[{"title":"DeepSceneSeg/SSMA","url":"https://github.com/DeepSceneSeg/SSMA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/self-supervised-model-adaptation-for","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","date":"2018-08-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/in2i-unsupervised-multi-image-to-image","title":"In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks","date":"2017-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unpaired-image-to-image-translation-using","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","date":"2017-03-30","rows_on_this_dataset":1,"code_links":190,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":6,"samples_unverified":25,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":40,"samples_ran":7,"samples_unverified":33,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}