Research map / Image generation / Image restoration
Learning Dynamic Guidance for Depth Image Enhancement
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use task-trained weighted analysis representation with stage-wise dynamic guidance | Guided depth upsampling · Middlebury noise-free test images | RMSE: Art: 2.57 -> 0.89 (×2); Books: 1.01 -> 0.47 (×2); Moebius: 0.91 -> 0.45 (×2) | Helped |
| Use task-trained weighted analysis representation with stage-wise dynamic guidance | Guided depth upsampling · NYU test images | RMSE: 1.97 -> 1.56 (×4); 3.39 -> 2.99 (×8); 5.63 -> 5.24 (×16) | Helped |
| Use task-trained weighted analysis representation with stage-wise dynamic guidance | Depth restoration · Depth restoration dataset [24] | RMSE: Art: 5.65 -> 4.96; Books: 2.24 -> 1.66; Moebius: 2.24 -> 1.76 | Helped |
Closest papers by meaning
- Robust Depth Enhancement via Polarization Prompt Fusion Tuning (CVPR 2024 · similarity 0.84)
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · similarity 0.84)
- Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion (CVPR 2025 · similarity 0.82)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.82)
- RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes (NeurIPS 2025 · similarity 0.82)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.82)
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.