Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination
- URL: http://arxiv.org/abs/2512.14200v1
- Date: Tue, 16 Dec 2025 08:47:56 GMT
- Title: Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination
- Authors: Zhuoxiao Li, Wenzong Ma, Taoyu Wu, Jinjing Zhu, Zhenchao Q, Shuai Zhang, Jing Ou, Yinrui Ren, Weiqing Qi, Guobin Shen, Hui Xiong, Wufan Zhao,
- Abstract summary: We introduceSkyLume, a dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling.<n>We collect data from 10 urban regions data comprising more than 100k high resolution UAV images.<n>We provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination.
- Score: 27.470486341807316
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Recent advances in Neural Radiance Fields and 3D Gaussian Splatting have demonstrated strong potential for large-scale UAV-based 3D reconstruction tasks by fitting the appearance of images. However, real-world large-scale captures are often based on multi-temporal data capture, where illumination inconsistencies across different times of day can significantly lead to color artifacts, geometric inaccuracies, and inconsistent appearance. Due to the lack of UAV datasets that systematically capture the same areas under varying illumination conditions, this challenge remains largely underexplored. To fill this gap, we introduceSkyLume, a large-scale, real-world UAV dataset specifically designed for studying illumination robust 3D reconstruction in urban scene modeling: (1) We collect data from 10 urban regions data comprising more than 100k high resolution UAV images (four oblique views and nadir), where each region is captured at three periods of the day to systematically isolate illumination changes. (2) To support precise evaluation of geometry and appearance, we provide per-scene LiDAR scans and accurate 3D ground-truth for assessing depth, surface normals, and reconstruction quality under varying illumination. (3) For the inverse rendering task, we introduce the Temporal Consistency Coefficient (TCC), a metric that measuress cross-time albedo stability and directly evaluates the robustness of the disentanglement of light and material. We aim for this resource to serve as a foundation that advances research and real-world evaluation in large-scale inverse rendering, geometry reconstruction, and novel view synthesis.
Related papers
- UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes [17.205790966354705]
UAVLight is a controlled-yet-real benchmark for illumination-robust 3D reconstruction.<n>Each scene is captured along repeatable, geo-referenced flight paths at multiple fixed times of day.<n>With standardized evaluation protocols across lighting conditions, UAVLight provides a reliable foundation for developing and benchmarking reconstruction methods.
arXiv Detail & Related papers (2025-11-26T16:38:29Z) - MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation [19.46962637673285]
MV-CoLight is a framework for illumination-consistent object compositing in 2D and 3D scenes.<n>We employ a Hilbert curve-based mapping to align 2D image inputs with 3D Gaussian scene representations seamlessly.<n> Experiments demonstrate state-of-the-art harmonized results across standard benchmarks and our dataset.
arXiv Detail & Related papers (2025-05-27T17:53:02Z) - Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes [3.612819935891695]
We develop the first public benchmark dataset for 3D reconstruction and novel view synthesis based on multiple calibrated ground-level, security-level, and airborne cameras.<n>We present datasets that pose real-world challenges, independently evaluate calibration of unposed cameras and quality of novel rendered views, demonstrate baseline performance using recent state-of-practice methods, and identify challenges for further research.
arXiv Detail & Related papers (2025-04-29T19:57:29Z) - AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis [57.249817395828174]
We propose a scalable framework combining pseudo-synthetic renderings from 3D city-wide meshes with real, ground-level crowd-sourced images.<n>The pseudo-synthetic data simulates a wide range of aerial viewpoints, while the real, crowd-sourced images help improve visual fidelity for ground-level images.<n>Using this hybrid dataset, we fine-tune several state-of-the-art algorithms and achieve significant improvements on real-world, zero-shot aerial-ground tasks.
arXiv Detail & Related papers (2025-04-17T17:57:05Z) - EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
arXiv Detail & Related papers (2025-03-26T02:47:27Z) - IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations [64.07859467542664]
Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics.<n>Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs.<n>We introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations.
arXiv Detail & Related papers (2024-12-16T18:52:56Z) - RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings.
Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor.
Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
arXiv Detail & Related papers (2024-06-14T07:54:25Z) - GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception.<n>Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
arXiv Detail & Related papers (2024-05-17T07:31:20Z) - Advancing Applications of Satellite Photogrammetry: Novel Approaches for Built-up Area Modeling and Natural Environment Monitoring using Stereo/Multi-view Satellite Image-derived 3D Data [0.0]
This dissertation explores several novel approaches based on stereo and multi-view satellite image-derived 3D geospatial data.
It introduces four parts of novel approaches that deal with the spatial and temporal challenges with satellite-derived 3D data.
Overall, this dissertation demonstrates the extensive potential of satellite photogrammetry applications in addressing urban and environmental challenges.
arXiv Detail & Related papers (2024-04-18T20:02:52Z) - StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
We present StableDreamer, a methodology incorporating three advances.
First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss.
Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
arXiv Detail & Related papers (2023-12-02T02:27:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.