Papers › Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

13 Nov 2020arXiv:2011.06961archive 2025-07-28

Daniel Seichter, Mona Köhler, Benjamin Lewandowski, Tim Wengefeld, Horst-Michael Gross

Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection, (semantic) mapping, and (semantic) navigation. In this paper, we propose an efficient and robust RGB-D segmentation approach that can be optimized to a high degree using NVIDIA TensorRT and, thus, is well suited as a common initial processing step in a complex system for scene analysis on mobile robots. We show that RGB-D segmentation is superior to processing RGB images solely and that it can still be performed in real time if the network architecture is carefully designed. We evaluate our proposed Efficient Scene Analysis Network (ESANet) on the common indoor datasets NYUv2 and SUNRGB-D and show that we reach state-of-the-art performance while enabling faster inference. Furthermore, our evaluation on the outdoor dataset Cityscapes shows that our approach is suitable for other areas of application as well. Finally, instead of presenting benchmark results only, we also show qualitative results in one of our indoor application scenarios.

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/ESANet officialmentioned in papermentioned on GitHubpytorch report
Barchid/RGBD-Seg mentioned on GitHubpytorch report
evilpanda009/rain-perception mentioned on GitHubpytorch 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

SegmentationSemantic SegmentationThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test ESANet-R34-NBt1D Mean IoU (class) 80.09% #53 of 105 Archive leaderboard report
Semantic Segmentation NYU Depth v2 ESANet (R34-NBt1D) Mean IoU 50.30 #65 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 ESANet (R18-NBt1D ) Mean IoU 48.17 #80 of 121 Archive leaderboard report
Semantic Segmentation SUN-RGBD CMX (B5) Mean IoU 48.17 #32 of 44 Archive leaderboard report
Semantic Segmentation THUD Robotic Dataset ESANet mIoU 78.42 #2 of 4 Archive leaderboard report
Semantic Segmentation UrbanLF ESANet mIoU (Real) n.a. #5 of 14 Archive leaderboard report
Semantic Segmentation UrbanLF ESANet mIoU (Syn) 79.43 #5 of 14 Archive leaderboard report
Thermal Image Segmentation RGB-T-Glass-Segmentation ESANet MAE 0.040 #3 of 22 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationPyramid Pooling ModuleReLUResidual BlockResidual Connection

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