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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add diffusion refinement on top of the ViT module (ablation) | D3-RSMDE · Japan+Korea | LPIPS: 0.305 -> 0.180 | Improved |
| add diffusion refinement on top of the ViT module (ablation) | D3-RSMDE · Southeast Asia | LPIPS: 0.503 -> 0.318 | Improved |
| add diffusion refinement on top of the ViT module (ablation) | D3-RSMDE · Mediterranean | LPIPS: 0.439 -> 0.290 | Improved |
| train ViT module with HDN loss instead of plain DPT (ablation) | DPT · Japan+Korea | MAE: 17.3 -> 12.8 | Improved |
| train ViT module with HDN loss instead of plain DPT (ablation) | DPT · Southeast Asia | LPIPS: 0.604 -> 0.503 | Improved |
| increase denoising steps from 3 to 6 (ablation) | D3-RSMDE (AEKL) · Japan+Korea | LPIPS: 0.199 -> 0.180 | Improved |
| increase denoising steps from 6 to 10 (ablation) | D3-RSMDE (AEKL) · Japan+Korea | LPIPS: 0.180 -> 0.187 | Hurt |
| increase denoising steps from 6 to 10 (ablation) | D3-RSMDE (VA_VAE) · Japan+Korea | LPIPS: 0.203 -> 0.324 | Hurt |
| use latent-space refinement with VAE instead of pixel space (ablation) | D3-RSMDE · RS3DBench | accuracy | No clear effect |
| use latent-space refinement with VAE instead of pixel space (ablation) | D3-RSMDE · RS3DBench | training speed: 54.91% | Improved |
| use latent-space refinement with VAE instead of pixel space (ablation) | D3-RSMDE · RS3DBench | training VRAM: 36.17% | Improved |
| use AEKL instead of VA_VAE as the autoencoder (ablation) | D3-RSMDE · Japan+Korea | LPIPS: 0.203 -> 0.180 | Improved |
Closest papers by meaning
- Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (CVPR 2024 · similarity 0.87)
- RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions (NeurIPS 2024 · similarity 0.87)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.86)
- Scalable Autoregressive Monocular Depth Estimation (CVPR 2025 · similarity 0.86)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.85)
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.
