AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?

John McCormac, Ankur Handa, Stefan Leutenegger, Andrew J. Davison

ICCV 2017 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 299 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
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · NYUv2 (13 class, val)mean IU: 33.7 -> 41.8Improved
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · NYUv2 (13 class, val)class average accuracy: 47.6 -> 56.0Improved
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · NYUv2 (13 class, val)pixel average accuracy: 60.2 -> 66.1Improved
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · SUN RGB-D (13 class, val)mean IU: 40.3 -> 43.8Improved
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · SUN RGB-D (13 class, val)class average accuracy: 56.8 -> 57.8Improved
pre-train on SceneNet RGB-D synthetic RGB instead of ImageNet VGG-16 initU-Net RGB · SUN RGB-D (13 class, val)pixel average accuracy: 71.2 -> 73.3Improved
add synthetic RGB pre-training vs no pre-training (ablation)U-Net RGB · NYUv2 (13 class, val)mean IU: 29.0 -> 41.8Improved
add synthetic RGB pre-training vs no pre-training (ablation)U-Net RGB · SUN RGB-D (13 class, val)mean IU: 36.5 -> 43.8Improved
add depth channel to synthetic pre-trained network (ablation)U-Net pre-trained on SceneNet · NYUv2 (13 class, val)mean IU: 41.8 -> 48.2Improved
add depth channel to synthetic pre-trained network (ablation)U-Net pre-trained on SceneNet · SUN RGB-D (13 class, val)mean IU: 43.8 -> 49.8Improved
add SceneNet pre-training to RGB-D network vs training from scratch (ablation)U-Net RGB-D · NYUv2 (13 class, val)mean IU: 36.9 -> 48.2Improved
add SceneNet pre-training to RGB-D network vs training from scratch (ablation)U-Net RGB-D · SUN RGB-D (13 class, val)mean IU: 41.4 -> 49.8Improved

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