Research map / 3D vision / Depth and stereo
Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments
Shuang Song, Debao Huang, Deyan Deng, Haolin Xiong, Yang Tang, Yajie Zhao, Rongjun Qin
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 |
|---|---|---|---|
| fine-tune on Olbedo (standard fine-tuning) | NIID-Net · MatrixCity (520 outdoor images) | PSNR: 12.782 -> 16.152 | Improved |
| fine-tune on Olbedo (standard fine-tuning) | NIID-Net · MatrixCity (520 outdoor images) | LPIPS: 0.793 -> 0.769 | Improved |
| LoRA fine-tune on Olbedo | Intrinsic Image Diffusion · MatrixCity (520 outdoor images) | PSNR: 15.594 -> 17.249 | Improved |
| LoRA fine-tune on Olbedo | Marigold-IID-Appearance · MatrixCity (520 outdoor images) | PSNR: 10.153 -> 17.118 | Improved |
| LoRA fine-tune on Olbedo | Marigold-IID-Appearance · MatrixCity (520 outdoor images) | LPIPS: 0.591 -> 0.461 | Improved |
| LoRA fine-tune on Olbedo | RGB<->X · MatrixCity (520 outdoor images) | PSNR: 15.050 -> 17.735 | Improved |
| LoRA fine-tune on Olbedo | RGB<->X · MatrixCity (520 outdoor images) | SSIM: 0.559 -> 0.611 | Improved |
| LoRA fine-tune on Olbedo | RGB<->X · MatrixCity (520 outdoor images) | LPIPS: 0.472 -> 0.413 | Improved |
| LoRA fine-tune on Olbedo | Intrinsic Image Diffusion · MatrixCity (520 outdoor images) | SSIM: 0.493 -> 0.531 | Improved |
| LoRA fine-tune on Olbedo | Marigold-IID-Appearance · MatrixCity (520 outdoor images) | SSIM: 0.508 -> 0.570 | Improved |
| fine-tune on Olbedo (standard fine-tuning) | NIID-Net · MatrixCity (520 outdoor images) | SSIM: 0.549 -> 0.594 | Improved |
Closest papers by meaning
- AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision (ECCV 2026 · similarity 0.88)
- SkyLume: A Large-Scale Multi-Illumination Aerial Benchmark for Urban Scene Reconstruction and Beyond (ECCV 2026 · similarity 0.88)
- The Sky's the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility (ECCV 2024 · similarity 0.87)
- Deep Sky Modeling for Single Image Outdoor Lighting Estimation (CVPR 2019 · similarity 0.86)
- AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis (CVPR 2025 · similarity 0.86)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · 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.
