Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

TL;DR

It is demonstrated that fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark, and applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins are illustrated.

Abstract

Intrinsic image decomposition (IID) of outdoor scenes is crucial for relighting, editing, and understanding large-scale environments, but progress has been limited by the lack of real-world datasets with reliable albedo and shading supervision. We introduce Olbedo, a large-scale aerial dataset for outdoor albedo--shading decomposition in the wild. Olbedo contains 5,664 UAV images captured across four landscape types, multiple years, and diverse illumination conditions. Each view is accompanied by multi-view consistent albedo and shading maps, metric depth, surface normals, sun and sky shading components, camera poses, and, for recent flights, measured HDR sky domes. These annotations are derived from an inverse-rendering refinement pipeline over multi-view stereo reconstructions and calibrated sky illumination, together with per-pixel confidence masks. We demonstrate that Olbedo enables state-of-the-art diffusion-based IID models, originally trained on synthetic indoor data, to generalize to real outdoor imagery: fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark. We further illustrate applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins. We release the dataset, baseline models, and an evaluation protocol to support future research in outdoor intrinsic decomposition and illumination-aware aerial vision.

Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments

TL;DR

It is demonstrated that fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark, and applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins are illustrated.

Abstract

Intrinsic image decomposition (IID) of outdoor scenes is crucial for relighting, editing, and understanding large-scale environments, but progress has been limited by the lack of real-world datasets with reliable albedo and shading supervision. We introduce Olbedo, a large-scale aerial dataset for outdoor albedo--shading decomposition in the wild. Olbedo contains 5,664 UAV images captured across four landscape types, multiple years, and diverse illumination conditions. Each view is accompanied by multi-view consistent albedo and shading maps, metric depth, surface normals, sun and sky shading components, camera poses, and, for recent flights, measured HDR sky domes. These annotations are derived from an inverse-rendering refinement pipeline over multi-view stereo reconstructions and calibrated sky illumination, together with per-pixel confidence masks. We demonstrate that Olbedo enables state-of-the-art diffusion-based IID models, originally trained on synthetic indoor data, to generalize to real outdoor imagery: fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark. We further illustrate applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins. We release the dataset, baseline models, and an evaluation protocol to support future research in outdoor intrinsic decomposition and illumination-aware aerial vision.
Paper Structure (42 sections, 10 equations, 19 figures, 1 table)

This paper contains 42 sections, 10 equations, 19 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Intrinsic Image Decomposition
  4. The Ground Truth Dataset Bottleneck
  5. Olbedo Dataset
  6. Overview
  7. Data Collection
  8. Temporal Image Collection
  9. Sky Radiance Capture
  10. Statistics and Coverage
  11. Ground-truth Albedo Curation
  12. Aerial Image Preprocessing
  13. Image Decomposition Framework
  14. Confidence Masks
  15. Validation
  16. ...and 27 more sections

Figures (19)

  • Figure 1: Landscapes of the Olbedo dataset. (cr: Google)
  • Figure 1: Comparison between in-camera JPEG (a) and RAW DNG (b) from the same scene. The JPEG image exhibits visible artifacts such as color clipping in highlights, loss of shadow details, and posterization effects due to aggressive compression and tone mapping. In contrast, the RAW DNG preserves a wider dynamic range and more accurate color representation, which are essential for reliable albedo–shading decomposition.
  • Figure 2: Sky radiance acquisition and representation. Left: exposure-bracketed raw sky images. Right: merged HDR sky dome in equirectangular format.
  • Figure 2: Additional examples from the Olbedo dataset. Rows from top to bottom: arena, office, residential, and park scenes.
  • Figure 3: Statistics of our multi-temporal albedo dataset. (a) Distribution of images per year. (b) Distribution of images per site. (c) Distribution of images per lighting condition.
  • ...and 14 more figures