Papers › Depth-Adapted CNNs for RGB-D Semantic Segmentation

Depth-Adapted CNNs for RGB-D Semantic Segmentation

8 Jun 2022arXiv:2206.03939archive 2025-07-28

Zongwei Wu, Guillaume Allibert, Christophe Stolz, Chao Ma, Cédric Demonceaux

Recent RGB-D semantic segmentation has motivated research interest thanks to the accessibility of complementary modalities from the input side. Existing works often adopt a two-stream architecture that processes photometric and geometric information in parallel, with few methods explicitly leveraging the contribution of depth cues to adjust the sampling position on RGB images. In this paper, we propose a novel framework to incorporate the depth information in the RGB convolutional neural network (CNN), termed Z-ACN (Depth-Adapted CNN). Specifically, our Z-ACN generates a 2D depth-adapted offset which is fully constrained by low-level features to guide the feature extraction on RGB images. With the generated offset, we introduce two intuitive and effective operations to replace basic CNN operators: depth-adapted convolution and depth-adapted average pooling. Extensive experiments on both indoor and outdoor semantic segmentation tasks demonstrate the effectiveness of our approach.

PaperPDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation NYU Depth v2 Z-ACN (ResNet-101) Mean IoU 51.24% #53 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Z-ACN (ResNet-50) Mean IoU 50.05% #66 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Z-ACN (ResNet-34) Mean IoU 49.15% #71 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Z-ACN (ResNet-18) Mean IoU 47.02% #87 of 121 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

Convolution

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