{"url":"/dataset/mcubes","name":"MCubeS","full_name":"Multimodal Material Segmentation Dataset","description_markdown":"Multimodal material segmentation (MCubeS) dataset contains 500 sets of images from 42 street scenes. Each scene has images for four modalities: RGB, angle of linear polarization (AoLP), degree of linear polarization (DoLP), and near-infrared (NIR). The dataset provides annotated ground truth labels for both material and semantic segmentation for every pixel. The dataset is divided training set with 302 image sets, validation set with 96 image sets, and test set with 102 image sets. Each image has  1224 x 1024 pixels and a total of 20 class labels per pixel.","description_withheld":null,"homepage":"https://github.com/kyotovision-public/multimodal-material-segmentation","introduced_date":"2022-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/multimodal-material-segmentation","title":"Multimodal Material Segmentation","first_author":"Yupeng Liang","url":null},"license":{"name":"MiT","url":"https://github.com/kyotovision-public/multimodal-material-segmentation/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Hyperspectral images","url":"/datasets/modality/hyperspectral-images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Image Segmentation","url":"/task/image-segmentation","datasets_with_task":"/datasets/task/image-segmentation"},{"name":"Material Recognition","url":"/task/material-recognition","datasets_with_task":"/datasets/task/material-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MCubeS"],"data_loaders":[{"repo":"https://github.com/1670839413/52","url":"https://paperswithcode.com/dataset/mcubes","frameworks":["pytorch"]}],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-mcubes","task":"Semantic Segmentation","dataset_variant":"MCubeS","rows":22,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"StitchFusion (RGB-A-D-N)","paper":"/paper/2408-01343","metrics":{"mIoU":"53.92"},"code_links":[{"title":"libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","url":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/memorysam-memorize-modalities-and-semantics","title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","date":"2025-03-09","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/2408-01343","title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","date":"2024-08-02","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/sharecmp-polarization-aware-rgb-p-semantic","title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation","date":"2023-12-06","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multimodal-transformer-for-material","title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","date":"2023-09-07","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/delivering-arbitrary-modal-semantic","title":"Delivering Arbitrary-Modal Semantic Segmentation","date":"2023-03-02","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multimodal-material-segmentation","title":"Multimodal Material Segmentation","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decoupled-dynamic-filter-networks","title":"Decoupled Dynamic Filter Networks","date":"2021-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-region-aware-convolution","title":"Dynamic Region-Aware Convolution","date":"2020-03-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/encoder-decoder-with-atrous-separable","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","date":"2018-02-07","rows_on_this_dataset":1,"code_links":78,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":72,"samples_ran":43,"samples_unverified":29,"pointer_only_for_licence":40,"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":4,"samples_harvested":84,"samples_ran":54,"samples_unverified":30,"pointer_only_for_licence":40,"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."}