Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
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 ARC instead of mix training | Depth prediction with real and synthetic training data · NYUv2 test | Rel: 0.200 -> 0.186 | Helped |
| Use ARC instead of mix training | Depth prediction with real and synthetic training data · Kitti test | Rel: 0.152 -> 0.143 | Helped |
| Add attention to style translation (ablation) | ARC depth prediction · NYUv2 test | Rel: 0.226 -> 0.189 | Helped |
| Add attention to style translation (ablation) | ARC depth prediction · Kitti test | Rel: 0.156 -> 0.147 | Helped |
| Add style translation to attention (ablation) | ARC depth prediction · NYUv2 test | Rel: 0.204 -> 0.189 | Helped |
| Add style translation to attention (ablation) | ARC depth prediction · Kitti test | Rel: 0.154 -> 0.147 | Helped |
| Add inpainting to attention (ablation) | ARC depth prediction · NYUv2 test | Rel: 0.204 -> 0.195 | Helped |
| Add inpainting to attention (ablation) | ARC depth prediction · Kitti test | Rel: 0.154 -> 0.152 | Helped |
| Add inpainting to attention and style translation (ablation) | ARC depth prediction · NYUv2 test | Rel: 0.189 -> 0.186 | Helped |
| Add inpainting to attention and style translation (ablation) | ARC depth prediction · Kitti test | Rel: 0.147 -> 0.143 | Helped |
| Use style translation only rather than mix training (ablation) | ARC depth prediction · NYUv2 test | Rel: 0.200 -> 0.226 | Hurt |
| Use style translation only rather than mix training (ablation) | ARC depth prediction · Kitti test | Rel: 0.152 -> 0.156 | Hurt |
Closest papers by meaning
- DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching (AAAI 2025 · similarity 0.87)
- Test-Time Adaptation for Depth Completion (CVPR 2024 · similarity 0.87)
- BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model (NeurIPS 2024 · similarity 0.86)
- Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment (CVPR 2024 · similarity 0.86)
- SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation (CVPR 2025 · similarity 0.86)
- Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors (CVPR 2025 · similarity 0.86)
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.