A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Filters
Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks. ...
Extensive experiments on NYU-Depth v2 and SUN RGB-D datasets demonstrate that our method achieves state-of-the-art results for monocular depth estimation and semantic segmentation. ...
In summary, the contributions of this paper are three folds: -Propose a novel joint Task-Recursive Learning (TRL) framework for semantic segmentation and depth estimation. ...
doi:10.1007/978-3-030-01249-6_15
fatcat:aikjy2xbsjabjfczjo2vwuspdi
Pattern-Structure Diffusion for Multi-Task Learning
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
and task-across pattern structures in the task-level space for joint depth estimation, segmentation and surface normal prediction. ...
Finally, the intra-task and inter-task pattern structures are jointly diffused among the task-level patterns, and encapsulated into an end-to-end PSD network to boost the performance of multi-task learning ...
Acknowledgement This work was supported by the National Natural Science Foundation of China (Grants Nos.61772276, 61906094, 61972204, U1713208) and the Natural Science Foundation of Jiangsu Province (Grants ...
doi:10.1109/cvpr42600.2020.00457
dblp:conf/cvpr/ZhouCXZWZ020
fatcat:cgolbmcyezhyvgowjxiwa4j2ou
Latent 3D Volume for Joint Depth Estimation and Semantic Segmentation from a Single Image
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a novel 3D representation, namely, a latent 3D volume, for joint depth estimation and semantic segmentation. ...
We will show that the latent 3D volume is beneficial to the tasks of depth estimation and semantic segmentation because these tasks require an understanding of the 3D structure of the scene. ...
Acknowledgments: Computational resources were provided by Aoyama Gakuin University Center for Advanced Information technology Research (CAIR). ...
doi:10.3390/s20205765
pmid:33053692
fatcat:mraupjui5ras5fswgoh3cunnri
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
network which simultaneously performs depth estimation and semantic segmentation on the synthetic data. ...
This demonstrates the usefulness of geometric information from synthetic data for cross-domain semantic segmentation. ...
: individually aligning both semantic segmentation and depth estimation; joint: aligning the joint output space of depth estimation and semantic segmentation, which is also our final output level adaptation ...
arXiv:1812.05040v2
fatcat:vp3wnkuoaff5hpgoy7htc32zfq
Competitive Simplicity for Multi-Task Learning for Real-Time Foggy Scene Understanding via Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a complex but competitive multi-task learning approach capable of performing in real-time semantic scene understanding and monocular depth estimation under foggy weather conditions ...
For optimal performance in semantic segmentation, our model generates depth to be used as complementary source information with RGB in the segmentation network. ...
As an overall loss for the depth estimation task, a joint depth loss is defined as follows: L joint−depth = L depth + L adv . (6)
E. ...
arXiv:2012.05304v1
fatcat:irpbfthy4rgbfh7tmpaw3vjlfi
Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Monocular depth estimation is a challenging task in scene understanding, with the goal to acquire the geometric properties of 3D space from 2D images. ...
Moreover, our proposed model is able to perform region-aware depth estimation by enforcing semantics consistency between stereo pairs. ...
This work is supported in part by the Ministry of Science and Technology of Taiwan under grant MOST 108-2634-F-002-018. ...
doi:10.1109/cvpr.2019.00273
dblp:conf/cvpr/ChenLLW19
fatcat:yxy47fjnnbchljkxlmge7fte3u
Survey on Semantic Stereo Matching / Semantic Depth Estimation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Stereo matching is one of the widely used techniques for inferring depth from stereo images owing to its robustness and speed. ...
Recent developments have shown that semantic cues from image segmentation can be used to improve the results of stereo matching. ...
Joint-Learning Approach: These approaches use a common architecture for both stereo matching and semantic segmentation in the initial stages to extract features that are generic for both the tasks and ...
arXiv:2109.10123v1
fatcat:clqvhhh6o5bwtfvv4bir3svwqy
DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation
2022
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In addition, we explore the joint semantic segmentation and depth estimation task and demonstrate that the proposed technique can efficiently perform both tasks simultaneously, outperforming state-of-art ...
We propose Depth-to-Space Net (DTS-Net), an effective technique for semantic segmentation using the efficient sub-pixel convolutional neural network. ...
We also provide the test and the evaluation codes of the proposed method at: https://github.com/HatemHosam/ DTS-Net which is created and accessed on 21 June 2021. ...
doi:10.3390/s22010337
pmid:35009879
pmcid:PMC8749585
fatcat:mvxugub4anbmbcpoybyrmm7dxa
Auxiliary Learning for Deep Multi-task Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We evaluate the proposed auxiliary module on pixel-wise prediction tasks, including semantic segmentation, depth estimation, and surface normal prediction with different network structures. ...
Multi-task learning (MTL) is an efficient solution to solve multiple tasks simultaneously in order to get better speed and performance than handling each single-task in turn. ...
(a) and (d): Semantic segmentation and depth estimation results of ResNet50-joint. (b) and (e): Semantic segmentation and depth estimation results of ResNet50-Auxi-all. (c) and (f): Ground truth. ...
arXiv:1909.02214v2
fatcat:s54gcmpghvfflhj3lmlctnukfy
Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Specifically, we study the correlation of 2D/3D pose estimation, body part segmentation and full-body depth estimation. ...
the most, 2D pose improves neither 3D pose nor full-body depth estimation. ...
In summary, ankle, wrist and elbow are the most difficult joints to learn. Again, we see those body parts and joints are difficult to predict for all tasks.
D. ...
arXiv:1905.03003v1
fatcat:wapz62r36rhuhavfkonldyvzwq
Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
On the one hand, we propose to explicitly learn the task feature correlation to strengthen the target semantic predictions with the help of target depth estimation. ...
Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. ...
Acknowledgement The contributions of Qin Wang and Olga Fink were funded by the Swiss National Science Foundation (SNSF) Grant no. PP00P2 176878. ...
arXiv:2104.13613v2
fatcat:6velaiarczhojkpyizv7app7le
Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
2021
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
On the one hand, we propose to explicitly learn the task feature correlation to strengthen the target semantic predictions with the help of target depth estimation. ...
Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. ...
Acknowledgement The contributions of Qin Wang and Olga Fink were funded by the Swiss National Science Foundation (SNSF) Grant no. PP00P2 176878. ...
doi:10.1109/iccv48922.2021.00840
fatcat:2qpvrotukzfyxg3mt4unzmhufy
Guest Editors' Introduction to the Special Issue on RGB-D Vision: Methods and Applications
2020
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The 26 accepted papers of this special issue can be grouped into six different main categories: (i) new sensing technologies, (ii) depth estimation and enhancement, (iii) simultaneous localization and ...
Compared to 2D images and 3D data (including depth images, point clouds and meshes), RGB-D images represent both the photometric and geometric information of a scene. ...
Yang proposes a task-recursive learning (TRL) framework to jointly and recurrently conduct three representative tasks including depth estimation, surface normal prediction and semantic segmentation. ...
doi:10.1109/tpami.2020.2976227
fatcat:dqt5dt3ymnesfikmgu2sxffdcu
Adversarial Attacks on Monocular Depth Estimation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Recent advances of deep learning have brought exceptional performance on many computer vision tasks such as semantic segmentation and depth estimation. ...
We then adapt several state-of-the-art attack methods for classification on the field of depth estimation. ...
Zhang et al proposed a task-recursive-learning framework for semantic segmentation and depth estimation [43] .
B. Adversarial Attacks White-box and black-box attacks. ...
arXiv:2003.10315v1
fatcat:mhfqoh3dsbcvjb7csi2rdalqvu
Future Segmentation Using 3D Structure
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Our framework is based on learnable sub-modules capable of predicting pixel-wise scene semantic labels, depth, and camera ego-motion of adjacent frames. ...
Predicting the future to anticipate the outcome of events and actions is a critical attribute of autonomous agents; particularly for agents which must rely heavily on real time visual data for decision ...
We further plan to extend this work and demonstrate its effectiveness, by predicting future events for better motion planning, e.g. in the context of human-robot interaction. ...
arXiv:1811.11358v1
fatcat:tbjpzays6fchznx6kekjcd3gyu
« Previous
Showing results 1 — 15 out of 4,185 results