Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras
We introduce the Satellite Neural Radiance Field (Sat-NeRF), a new end-to-end model for learning multi-view satellite photogrammetry in the wild. Sat-NeRF combines some of the latest trends in neural rendering with native satellite camera models, represented by rational polynomial coefficient (RPC) functions. The proposed method renders new views and infers surface models of similar quality to those obtained with traditional state-of-the-art stereo pipelines. Multi-date images exhibit significant changes in appearance, mainly due to varying shadows and transient objects (cars, vegetation). Robustness to these challenges is achieved by a shadow-aware irradiance model and uncertainty weighting to deal with transient phenomena that cannot be explained by the position of the sun. We evaluate Sat-NeRF using WorldView-3 images from different locations and stress the advantages of applying a bundle adjustment to the satellite camera models prior to training. This boosts the network performance and can optionally be used to extract additional cues for depth supervision.
Code (1)
Tasks
NeRFNeural RenderingSimilar Papers 제목 키워드 기반
Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry
We present a new generic method for shadow-aware multi-view satellite photogrammetry of Earth Observation scenes. Our proposed method, the Shadow Neural Radiance Field (S-NeRF) follows recent advances in implicit volumet…
Earth ObservationImage ReconstructionNeRFNovel View Synthesis+2Gaussian Splatting for Efficient Satellite Image Photogrammetry
Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show h…
Earth ObservationNeRFComparative Analysis of Novel View Synthesis and Photogrammetry for 3D Forest Stand Reconstruction and extraction of individual tree parameters
Accurate and efficient 3D reconstruction of trees is crucial for forest resource assessments and management. Close-Range Photogrammetry (CRP) is commonly used for reconstructing forest scenes but faces challenges like lo…
3DGS3D ReconstructionNeRFNovel View SynthesisTransient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction
Neural radiance fields (NeRFs) have become a ubiquitous tool for modeling scene appearance and geometry from multiview imagery. Recent work has also begun to explore how to use additional supervision from lidar or depth …
3D ReconstructionAutonomous DrivingNeRFMU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
Generalizable Neural Radiance Fields (GeNeRFs) enable high-quality scene reconstruction from sparse views and can generalize to unseen scenes. However, in real-world settings, transient distractors break cross-view struc…