Datasets › MCubeS
MCubeS (Multimodal Material Segmentation Dataset)
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.
Benchmarks archive 2025-07-28
All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Semantic Segmentation | MCubeS | StitchFusion (RGB-A-D-N) mIoU 53.92 | StitchFusion: Weaving Any Visual Modalities to Enhance... | libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation | 22 | Compare |
Papers archive 2025-07-28
9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 19. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation | 1 | 3 | 9 Mar 2025 | not harvested |
| StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation | 1 | 5 | 2 Aug 2024 | not harvested |
| ShareCMP: Polarization-Aware RGB-P Semantic Segmentation | 1 | 3 | 6 Dec 2023 | ran 3 of 3 samples (0 unverified) |
| MMSFormer: Multimodal Transformer for Material and Semantic Segmentation | 1 | 4 | 7 Sep 2023 | not harvested |
| Delivering Arbitrary-Modal Semantic Segmentation | 1 | 3 | 2 Mar 2023 | ran 6 of 7 samples (1 unverified) |
| Multimodal Material Segmentation | 1 | 1 | 1 Jan 2022 | not harvested |
| Decoupled Dynamic Filter Networks | 1 | 1 | 29 Apr 2021 | ran 2 of 2 samples (0 unverified) |
| Dynamic Region-Aware Convolution | 0 | 1 | 27 Mar 2020 | not harvested |
| Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation | 78 | 1 | 7 Feb 2018 | ran 43 of 72 samples (29 unverified; 40 pointer-only for licence) |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- MCubeS
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections