AI Paper Atlas

Research map / 3D vision / Depth and stereo

D3-RSMDE: 40× Faster and High-Fidelity Remote Sensing Monocular Depth Estimation

Ruizhi Wang, Weihan Li, Zunlei Feng, Haofei Zhang, Mingli Song, Jiayu Wang, Jie Song, Li Sun

AAAI 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 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
add diffusion refinement on top of the ViT module (ablation)D3-RSMDE · Japan+KoreaLPIPS: 0.305 -> 0.180Improved
add diffusion refinement on top of the ViT module (ablation)D3-RSMDE · Southeast AsiaLPIPS: 0.503 -> 0.318Improved
add diffusion refinement on top of the ViT module (ablation)D3-RSMDE · MediterraneanLPIPS: 0.439 -> 0.290Improved
train ViT module with HDN loss instead of plain DPT (ablation)DPT · Japan+KoreaMAE: 17.3 -> 12.8Improved
train ViT module with HDN loss instead of plain DPT (ablation)DPT · Southeast AsiaLPIPS: 0.604 -> 0.503Improved
increase denoising steps from 3 to 6 (ablation)D3-RSMDE (AEKL) · Japan+KoreaLPIPS: 0.199 -> 0.180Improved
increase denoising steps from 6 to 10 (ablation)D3-RSMDE (AEKL) · Japan+KoreaLPIPS: 0.180 -> 0.187Hurt
increase denoising steps from 6 to 10 (ablation)D3-RSMDE (VA_VAE) · Japan+KoreaLPIPS: 0.203 -> 0.324Hurt
use latent-space refinement with VAE instead of pixel space (ablation)D3-RSMDE · RS3DBenchaccuracyNo clear effect
use latent-space refinement with VAE instead of pixel space (ablation)D3-RSMDE · RS3DBenchtraining speed: 54.91%Improved
use latent-space refinement with VAE instead of pixel space (ablation)D3-RSMDE · RS3DBenchtraining VRAM: 36.17%Improved
use AEKL instead of VA_VAE as the autoencoder (ablation)D3-RSMDE · Japan+KoreaLPIPS: 0.203 -> 0.180Improved

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