Papers › Multimodal Material Segmentation

Multimodal Material Segmentation

1 Jan 2022CVPR 2022 1archive 2025-07-28

Yupeng Liang, Ryosuke Wakaki, Shohei Nobuhara, Ko Nishino

Recognition of materials from their visual appearance is essential for computer vision tasks, especially those that involve interaction with the real world. Material segmentation, i.e., dense per-pixel recognition of materials, remains challenging as, unlike objects, materials do not exhibit clearly discernible visual signatures in their regular RGB appearances. Different materials, however, do lead to different radiometric behaviors, which can often be captured with non-RGB imaging modalities. We realize multimodal material segmentation from RGB, polarization, and near-infrared images. We introduce the MCubeS dataset (from MultiModal Material Segmentation) which contains 500 sets of multimodal images capturing 42 street scenes. Ground truth material segmentation as well as semantic segmentation are annotated for every image and pixel. We also derive a novel deep neural network, MCubeSNet, which learns to focus on the most informative combinations of imaging modalities for each material class with a newly derived region-guided filter selection (RGFS) layer. We use semantic segmentation, as a prior to "guide" this filter selection. To the best of our knowledge, our work is the first comprehensive study on truly multimodal material segmentation. We believe our work opens new avenues of practical use of material information in safety critical applications.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Material SegmentationSegmentationSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

MCubeSMCubeS (P)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation MCubeS MCubeSNet (RGB-A-D-N) mIoU 42.86% #19 of 22 Archive leaderboard report
Semantic Segmentation UPLight MCubeSNet (RGB-AoLP) mIoU 82.64 #7 of 8 Archive leaderboard report
Semantic Segmentation UPLight MCubeSNet (RGB-DoLP) mIoU 80.80 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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