Description
Inspired by the spatial propagation mechanism utilized in the depth completion task \cite{NLSPN}, we introduce a normal incorporated non-local disparity propagation module in which we hub NDP to generate non-local affinities and offsets for spatial propagation at the disparity level. The motivation lies that the sampled pixels for edges and occluded regions are supposed to be selected. The propagation process aggregates disparities via plane affinity relations, which alleviates the phenomenon of disparity blurring at object edges due to frontal parallel windows. And the disparities in occluded areas are also optimized at the same time by being propagated from non-occluded areas where the predicted disparities are with high confidence.
Papers Using This Method
Spiking Neural Networks for SAR Interferometric Phase Unwrapping: A Theoretical Framework for Energy-Efficient Processing2025-06-25DenseFormer: Learning Dense Depth Map from Sparse Depth and Image via Conditional Diffusion Model2025-03-31Parallel Sequence Modeling via Generalized Spatial Propagation Network2025-01-21Real-Time Localization and Bimodal Point Pattern Analysis of Palms Using UAV Imagery2024-10-14Angular Spread Statistics for 6.75 GHz FR1(C) and 16.95 GHz FR3 Mid-Band Frequencies in an Indoor Hotspot Environment2024-09-04On the dynamics of convolutional recurrent neural networks near their critical point2024-05-22Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement2024-04-30Tri-Perspective View Decomposition for Geometry-Aware Depth Completion2024-03-22Digging Into Normal Incorporated Stereo Matching2024-02-28Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency2023-12-23MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo2023-09-23RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion2023-09-01Revisiting Deformable Convolution for Depth Completion2023-08-03BEV@DC: Bird's-Eye View Assisted Training for Depth Completion2023-01-01Robust Sum-Rate Maximization in Transmissive RMS Transceiver-Enabled SWIPT Networks2022-12-10GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs2022-10-19