S Jiang, K You, Y Li, D Weng… - Geo-spatial Information …, 2024 - Taylor & Francis
ABSTRACT 3D reconstruction plays an increasingly important role in modern photogrammetric systems. Conventional satellite or aerial-based remote sensing (RS) …
In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as panoramic 3D cameras often produce 360∘ depth with missing data in complex scenes. Its …
Standard MSE or MAE loss function is commonly used in limited field-of-vision depth completion, treating each pixel equally under a basic assumption that all pixels have same …
C Gava, V Mukunda, T Habtegebrial… - Proceedings of the …, 2023 - openaccess.thecvf.com
Traditionally, spherical keypoint matching has been performed using greedy algorithms, such as Nearest Neighbors (NN) search. NN based algorithms often lead to erroneous or …
We propose a new system for automatic 2D floorplan reconstruction that is enabled by SALVe, our novel pairwise learned alignment verifier. The inputs to our system are sparsely …
For a monocular 360° image, depth estimation is a challenging because the distortion increases along the latitude. To perceive the distortion, existing methods devote to …
We present a cross-domain inference technique that learns from synthetic data to estimate depth and normals for in-the-wild omnidirectional 3D scenes encountered in real-world …
Z Teng, J Zhang, K Yang, K Peng… - Proceedings of the …, 2024 - openaccess.thecvf.com
Seeing only a tiny part of the whole is not knowing the full circumstance. Bird's-eye-view (BEV) perception, a process of obtaining allocentric maps from egocentric views, is restricted …
No existing spherical convolutional neural network (CNN) framework is both computationally scalable and rotationally equivariant. Continuous approaches capture rotational …