AI Paper Atlas

Research map / Detection and segmentation / CNN features

Depth-aware CNN for RGB-D Segmentation

Weiyue Wang, Ulrich Neumann

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 323 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add depth-aware convolution to the lower layers (Conv1_1 to Conv3_1) in addition to upper layers (ablation)D-CNN (VGG-16) · NYUv2 test (from scratch)mIoU: 22.4 -> 27.8Improved
add depth-aware average pooling (ablation)D-CNN (VGG-16) · NYUv2 test (from scratch)mIoU: 27.4 -> 27.8Improved
replace standard convolution with depth-aware operationsDeepLab VGG-16 · NYUv2 test (from scratch)mIoU: 15.9 -> 27.8Improved
use D-CNN instead of two-stream HHA networkDeepLab VGG-16 · NYUv2 test (from scratch)mIoU: 21.9 -> 27.8Improved
replace standard convolution with depth-aware operationsDeepLab VGG-16 · SUN-RGBD test (from scratch)mIoU: 22.8 -> 29.7Improved
replace standard convolution with depth-aware operationsDeepLab VGG-16 · SID Area 5 (from scratch)mIoU: 35.5 -> 39.5Improved
add depth-aware convolution to ResNet-50 encoderResNet-50 · NYUv2 test (pretrained, ResNet-50)mIoU: 38.8 -> 41.5Improved
add HHA encoding stream to D-CNND-CNN · NYUv2 test (pretrained)mIoU: 41.0 -> 43.9Improved
add HHA encoding stream to D-CNND-CNN · NYUv2 test (from scratch)mIoU: 27.8 -> 26.2Hurt
increase alpha in depth similarity from 8.3 to 20 (ablation)D-CNN · NYUv2 test (from scratch)mIoU: 27.8 -> 24.9Hurt
decrease alpha in depth similarity from 8.3 to 2.5 (ablation)D-CNN · NYUv2 test (from scratch)mIoU: 27.8 -> 25.3Hurt
use binary clipped depth similarity instead of exponential similarity (ablation)D-CNN · NYUv2 test (from scratch)mIoU: 27.8 -> 20.1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy