AI Paper Atlas

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

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

Ji Hou, Xiaoliang Dai, Zijian He, Angela Dai, Matthias Nießner

CVPR 2023 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 0 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 with masked RGB and sparse depth to reconstruct dense depthViT-B · ScanNet 2D semantic segmentationmIoU: 63.3 -> 66.7Improved
Pre-train with masked RGB and sparse depth to reconstruct dense depthViT · ScanNet 2D object detectionAP@0.5: +4.3 AP@0.5Improved
Pre-train with masked RGB and sparse depth to reconstruct dense depthViT · ScanNet 2D instance segmentationAP@0.5: +3.8 AP@0.5Improved
Keep only 20.0% of RGB patches and include 20.0% of depth patches (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 65.2 -> 66.7Improved
Keep 20.0% rather than 50.0% of RGB patches, with 20.0% depth patches (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 65.9 -> 66.7Improved
Keep 20.0% rather than 80.0% of RGB patches, with 20.0% depth patches (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 64.8 -> 66.7Improved
Use 20.0% rather than 80.0% depth patches while keeping RGB at 20.0% (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 65.5 -> 66.7Improved
Add RGB reconstruction loss alongside depth reconstruction (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 66.7 -> 65.6Hurt
Normalize predictions and targets in the reconstruction loss (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: +0.8%Improved
Remove Stage-I ImageNet initialization (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoUHurt
Apply Mask3D after MAE rather than training both together (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 63.3 -> 66.3Improved
Apply MAE after Mask3D rather than MAE before Mask3D (ablation)Mask3D pre-training · ScanNet 2D semantic segmentationmIoU: 66.3 -> 63.1Hurt

Later papers that compared with this method

4 later accepted papers report Mask3D as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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