Towards Interpretable Deep Networks for Monocular Depth Estimation

You, Zunzhi; Tsai, Yi-Hsuan; Chiu, Wei-Chen; Li, Guanbin

doi:10.1109/iccv48922.2021.01264

Cited by 11 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hu et al attempted to determine the most relevant sparse pixels for depth estimation [17]. You et al first determined the depth selectivity of some hidden units, which showed good insights for interpreting monocular depth estimation models [18]. Zhi et al proposed a novel disentangled latent Transformer model based on the multi-level interpretation [19].…”

Section: Pixel-wise Dense Predictionmentioning

confidence: 99%

HeightNet: Monocular Object Height Estimation

Kim

Kim²,

Lee³

et al. 2023

Electronics

View full text Add to dashboard Cite

Monocular depth estimation is a traditional computer vision task that predicts the distance of each pixel relative to the camera from one 2D image. Relative height information about objects lying on a ground plane can be calculated through several processing steps from the depth image. In this paper, we propose a height estimation method for directly predicting the height of objects from a 2D image. The proposed method utilizes an encoder-decoder network for pixel-wise dense prediction based on height consistency. We used the CARLA simulator to generate 40,000 training datasets from different positions in five areas within the simulator. The experimental results show that the object’s height map can be estimated regardless of the camera’s location.

show abstract

Section: Pixel-wise Dense Predictionmentioning

confidence: 99%

HeightNet: Monocular Object Height Estimation

Kim

Kim²,

Lee³

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…The lack of interpretability hinders the application of monocular depth estimation to downstream tasks (e.g., autonomous driving) [42]. Most existing solutions devote to achieving more advanced performance but ignore the model's interpretability.…”

Section: Interpretable Analysismentioning

confidence: 99%

“…Or they just backward inference how the model works according to its advanced performance. Even You et al [42] enhance the interpretability by the depth selectivity of the model's hidden units. But the process of selecting hidden units is based on observation, which is also a backward inference.…”

Section: Interpretable Analysismentioning

confidence: 99%

Neural Contourlet Network for Monocular 360° Depth Estimation

Shen

Lin

Nie

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

For a monocular 360°image, depth estimation is a challenging because the distortion increases along the latitude. To perceive the distortion, existing methods devote to designing a deep and complex network architecture. In this paper, we provide a new perspective that constructs an interpretable and sparse representation for a 360°image. Considering the importance of the geometric structure in depth estimation, we utilize the contourlet transform to capture an explicit geometric cue in the spectral domain and integrate it with an implicit cue in the spatial domain. Specifically, we propose a neural contourlet network consisting of a convolutional neural network and a contourlet transform branch. In the encoder stage, we design a spatial-spectral fusion module to effectively fuse two types of cues. Contrary to the encoder, we employ the inverse contourlet transform with learned low-pass subbands and band-pass directional subbands to compose the depth in the decoder. Experiments on the three popular 360°panoramic image datasets demonstrate that the proposed approach outperforms the state-of-the-art schemes with faster convergence. Code is available at https://github.com/ zhijieshen-bjtu/Neural-Contourlet-Network-for-MODE.

show abstract

“…To integrate visual odometry (VO) or the SLAM system into depth estimation, the authors of [10,12,13] presented a neural network to correct classical VO estimators in a selfsupervised manner and enhance geometric constraints. Self-supervised depth estimation, using the pose and depth between two adjacent frames, establishes a depth reprojection error and image reconstruction error [14][15][16][17]. In a monocular depth self-supervised estimation, the depth value estimated by the depth estimation network (DepthNet) and the pose between adjacent images have a decisive influence on the depth estimation result.…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor Fusion Self-Supervised Deep Odometry and Depth Estimation

et al. 2022

View full text Add to dashboard Cite

This paper presents a new deep visual-inertial odometry and depth estimation framework for improving the accuracy of depth estimation and ego-motion from image sequences and inertial measurement unit (IMU) raw data. The proposed framework predicts ego-motion and depth with absolute scale in a self-supervised manner. We first capture dense features and solve the pose by deep visual odometry (DVO), and then combine the pose estimation pipeline with deep inertial odometry (DIO) by the extended Kalman filter (EKF) method to produce the sparse depth and pose with absolute scale. We then join deep visual-inertial odometry (DeepVIO) with depth estimation by using sparse depth and the pose from DeepVIO pipeline to align the scale of the depth prediction with the triangulated point cloud and reduce image reconstruction error. Specifically, we use the strengths of learning-based visual-inertial odometry (VIO) and depth estimation to build an end-to-end self-supervised learning architecture. We evaluated the new framework on the KITTI datasets and compared it to the previous techniques. We show that our approach improves results for ego-motion estimation and achieves comparable results for depth estimation, especially in the detail area.

show abstract

Towards Interpretable Deep Networks for Monocular Depth Estimation

Cited by 11 publications

References 31 publications

HeightNet: Monocular Object Height Estimation

HeightNet: Monocular Object Height Estimation

Neural Contourlet Network for Monocular 360° Depth Estimation

Multi-Sensor Fusion Self-Supervised Deep Odometry and Depth Estimation

Contact Info

Product

Resources

About