Browse > Computer Vision > Depth Estimation > Stereo Depth Estimation

Stereo Depth Estimation Edit

10 papers with code · Computer Vision

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach

26 Mar 2018NVIDIA-AI-IOT/redtail

Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large$-$a particularly relevant result due to the prevalent reliance upon monocular cameras by vehicles that are expected to be self-driving.

686

Anytime Stereo Image Depth Estimation on Mobile Devices

26 Oct 2018mileyan/AnyNet

Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints.

206

Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs.

197

Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve

5 Dec 2019puzzlepaint/camera_calibration

In contrast, generic camera models allow for very accurate calibration due to their flexibility.

128

Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

14 Jun 2019mileyan/Pseudo_Lidar_V2

In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation.

92

UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos

In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption.

77

360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume

11 Nov 2019albert100121/360SD-Net

Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images.

46

Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment.

41

Octave Deep Plane-Sweeping Network: Reducing Spatial Redundancy for Learning-Based Plane-Sweeping Stereo

Inspired by octave convolution, we divide image features into high and low spatial frequency features, and two cost volumes are generated from these using our proposed plane-sweeping module.

9

Efficient Attention: Attention with Linear Complexities

4 Dec 2018cmsflash/efficient-attention

To remedy this drawback, this paper proposes a novel efficient attention mechanism, which is equivalent to dot-product attention but has substantially less memory and computational costs.

8