29 citations · 50 across the 5 of their papers we have counts for
5 papers
SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation
Fisseha Admasu Ferede, Madhusudhanan Balasubramanian
Inaccurate optical flow estimates in and near occluded regions, and out-of-boundary regions are two of the current significant limitations of optical flow estimation algorithms. Re…
Multi-Resolution Factor Graph Based Stereo Correspondence Algorithm
Hanieh Shabanian, Madhusudhanan Balasubramanian
A dense depth-map of a scene at an arbitrary view orientation can be estimated from dense view correspondences among multiple lower-dimensional views of the scene. These low-dimens…
A Novel Factor Graph-Based Optimization Technique for Stereo Correspondence Estimation
Hanieh Shabanian, Madhusudhanan Balasubramanian
Dense disparities among multiple views is essential for estimating the 3D architecture of a scene based on the geometrical relationship among the scene and the views or cameras. Sc…
DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction
Ali Salehi, Madhusudhanan Balasubramanian
Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approac…
DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction
Ali Salehi, Madhusudhanan Balasubramanian
Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designe…