StereoDRNet: Dilated Residual Stereo Net
We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed depth refinement architecture, predicts view-consistent disparity and occlusion maps that helps the fusion system to produce geometrically consistent reconstructions. We utilize 3D dilated convolutions in our proposed cost filtering network that yields better filtering while almost halving the computational cost in comparison to state of the art cost filtering architectures.For feature extraction we use the Vortex Pooling architecture. The proposed method achieves state of the art results in KITTI 2012, KITTI 2015 and ETH 3D stereo benchmarks. Finally, we demonstrate that our system is able to produce high fidelity 3D scene reconstructions that outperforms the state of the art stereo system.
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
StereoDRNet: Dilated Residual StereoNet
We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed dept…
3D ReconstructionStereo Depth EstimationStereo Waterdrop Removal with Row-wise Dilated Attention
Existing vision systems for autonomous driving or robots are sensitive to waterdrops adhered to windows or camera lenses. Most recent waterdrop removal approaches take a single image as input and often fail to recover th…
Autonomous DrivingLearning a Dilated Residual Network for SAR Image Despeckling
In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose a novel deep learning approach by learning a non-linear end-to-end mapping between the n…
Sar Image DespecklingAutomatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net
X-ray images of the lower limb bone are the most commonly used imaging modality for clinical studies, and segmentation of the femur and tibia in an X-ray image is helpful for many medical studies such as diagnosis, surge…
SegmentationDilated Deep Residual Network for Image Denoising
Variations of deep neural networks such as convolutional neural network (CNN) have been successfully applied to image denoising. The goal is to automatically learn a mapping from a noisy image to a clean image given trai…
Color Image DenoisingDenoisingimage-classificationImage Classification+1