Papers › Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments

Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments

10 Jul 2022arXiv:2207.04526archive 2025-07-28

Daniel Seichter, Söhnke Benedikt Fischedick, Mona Köhler, Horst-Michael Groß

Semantic scene understanding is essential for mobile agents acting in various environments. Although semantic segmentation already provides a lot of information, details about individual objects as well as the general scene are missing but required for many real-world applications. However, solving multiple tasks separately is expensive and cannot be accomplished in real time given limited computing and battery capabilities on a mobile platform. In this paper, we propose an efficient multi-task approach for RGB-D scene analysis~(EMSANet) that simultaneously performs semantic and instance segmentation~(panoptic segmentation), instance orientation estimation, and scene classification. We show that all tasks can be accomplished using a single neural network in real time on a mobile platform without diminishing performance - by contrast, the individual tasks are able to benefit from each other. In order to evaluate our multi-task approach, we extend the annotations of the common RGB-D indoor datasets NYUv2 and SUNRGB-D for instance segmentation and orientation estimation. To the best of our knowledge, we are the first to provide results in such a comprehensive multi-task setting for indoor scene analysis on NYUv2 and SUNRGB-D.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tui-nicr/emsanet officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
tui-nicr/nicr-scene-analysis-datasets mentioned on GitHubpytorchApache-2.0 report

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

Instance SegmentationPanoptic SegmentationScene ClassificationScene Classification (unified classes)Scene UnderstandingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation NYU Depth v2 EMSANet PQ 47.38 #2 of 2 Archive leaderboard report
Panoptic Segmentation SUN-RGBD EMSANet PQ 52.84 #1 of 1 Archive leaderboard report
Semantic Segmentation NYU Depth v2 EMSANet (2x ResNet-34 NBt1D, finetuned) Mean IoU 53.34% #37 of 121 Archive leaderboard report
Semantic Segmentation SUN-RGBD DPLNet Mean IoU 48.47% #30 of 44 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