AI Paper Atlas

Research map / 3D vision / Depth and stereo

DustNet++: Deep Learning-Based Visual Regression for Dust Density Estimation

Andreas Michel, Martin Weinmann, Jannick Kuester, Faisal AlNasser, Tomás Gómez, Mark J. Falvey, Rainer Schmitz, Wolfgang Middelmann, Stefan Hinz

IJCV 2025 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 4 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 MBConv (ablation)DustNet++ Swin-L · Meteodata dustMAE: 13.74 -> 12.63Improved
add window attention to grid attention (ablation)DustNet++ Swin-L · Meteodata dustMAE: 17.94 -> 12.63Improved
add grid attention to window attention (ablation)DustNet++ Swin-L · Meteodata dustMAE: 15.62 -> 12.63Improved
add vanilla MSA alongside cross attention (ablation)DustNet++ Swin-L · Meteodata dustMAE: 18.93 -> 12.63Improved
add cross multi-axis attention to vanilla attention (ablation)DustNet++ Swin-L · Meteodata dustMAE: 15.46 -> 12.63Improved
use checkpoint wrapper to double batch size (ablation)DustNet S ResNet101 · Meteodata dustMAE: 19.27 -> 14.10Improved
use checkpoint wrapper to double batch size (ablation)PixelFormer Swin-B · Meteodata dustMAE: 21.53 -> 17.43Improved
use checkpoint wrapper for NewCRF Swin-B (ablation)NewCRF Swin-B · Meteodata dustMAE: 20.00 -> 20.83Hurt
use Swin-L backbone instead of ResNet101DustNet++ · Meteodata dust (single image)MAE: 13.95 -> 12.63Improved
add a second input image (temporal)DustNet++ Swin-L · Meteodata dustMAE: 12.63 -> 11.73Improved
use DustNet++ instead of DustNet SSwin-L · Meteodata dust (single image)IoU: 0.793 -> 0.784Mixed
use DustNet++ instead of DustNet S for generalizationSwin-L · URDE RandomDataset_897IoU: 0.618 -> 0.631Improved

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