2T-UNET: A Two-Tower UNet with Depth Clues for Robust Stereo Depth Estimation

10/27/2022
by   Rohit Choudhary, et al.
0

Stereo correspondence matching is an essential part of the multi-step stereo depth estimation process. This paper revisits the depth estimation problem, avoiding the explicit stereo matching step using a simple two-tower convolutional neural network. The proposed algorithm is entitled as 2T-UNet. The idea behind 2T-UNet is to replace cost volume construction with twin convolution towers. These towers have an allowance for different weights between them. Additionally, the input for twin encoders in 2T-UNet are different compared to the existing stereo methods. Generally, a stereo network takes a right and left image pair as input to determine the scene geometry. However, in the 2T-UNet model, the right stereo image is taken as one input and the left stereo image along with its monocular depth clue information, is taken as the other input. Depth clues provide complementary suggestions that help enhance the quality of predicted scene geometry. The 2T-UNet surpasses state-of-the-art monocular and stereo depth estimation methods on the challenging Scene flow dataset, both quantitatively and qualitatively. The architecture performs incredibly well on complex natural scenes, highlighting its usefulness for various real-time applications. Pretrained weights and code will be made readily available.

READ FULL TEXT

page 1

page 5

page 6

page 7

research
12/31/2018

Unsupervised monocular stereo matching

At present, deep learning has been applied more and more in monocular im...
research
06/21/2022

MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-exposure Stereo Images for HDR 3D Applications

Display technologies have evolved over the years. It is critical to deve...
research
02/02/2022

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation

Omnidirectional 3D information is essential for a wide range of applicat...
research
05/04/2023

Edge-aware Consistent Stereo Video Depth Estimation

Video depth estimation is crucial in various applications, such as scene...
research
10/21/2022

Context-Enhanced Stereo Transformer

Stereo depth estimation is of great interest for computer vision researc...
research
10/04/2018

Learning Depth with Convolutional Spatial Propagation Network

Depth prediction is one of the fundamental problems in computer vision. ...
research
06/05/2023

Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data

Nowadays, robotics, AR, and 3D modeling applications attract considerabl...

Please sign up or login with your details

Forgot password? Click here to reset