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.
Filters
Wasserstein Distances for Stereo Disparity Estimation
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. ...
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. ...
It is compatible with most existing stereo depth or disparity estimation approaches -we only need to add an additional offset branch and replace the commonly used regression loss by the Wasserstein distance ...
arXiv:2007.03085v2
fatcat:cjdg3swjuve3xlhqpryv6ll6ju
Motion Language of Stereo Image Sequence
2017
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
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 2018; you can also visit the original URL.
The file type is application/pdf.
These two operations extract a string of words of motion in front of the robots from stereo images captured by a robot-mounted camera system. ...
This paper proposes a method for the symbolisation of temporal changes of the environments around the autonomous robot in a work space using the scene flow field for recognition of events. ...
The KLT with piecewise-linear and locally quadratic constrains were used for the computation of stereo disparities between stereo pair images and optical flow between frames in each image sequence. ...
doi:10.1109/cvprw.2017.160
dblp:conf/cvpr/KatoII17
fatcat:26md73nm7bcazgabhpusuhy2tq
Environment reconstruction on depth images using Generative Adversarial Networks
[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.
Our final contribution is a loss function focused on disparity data and a GAN able to extract depth features and estimate depth data by inpainting disparity images. ...
Stereo cameras collect environment information at many levels, e.g., depth, color, texture, shape, which guarantee ample knowledge about the surroundings. ...
[3] introduce their WGAN loss function based on the Wasserstein distance metric. ...
arXiv:1912.03992v1
fatcat:27s4w2y4ljfe5k43bsdzkio7me
SDF-MAN: Semi-Supervised Disparity Fusion with Multi-Scale Adversarial Networks
2019
Remote Sensing
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.
Other Versions
Assuming a Markov Random Field for the refined disparity map produces better estimates of the true disparity distribution. ...
Uncertainty estimation and complex disparity relationships among pixels limit the accuracy and robustness of existing methods and there is no standard method for fusion of different kinds of depth data ...
We thank Chengyang Zhao, Marija Jegorova and Timothy Hospedales for giving us good advice on this paper. ...
doi:10.3390/rs11050487
fatcat:s3yp4j72bzen3gaywsie5hkwpm
A Conditional Adversarial Network for Scene Flow Estimation
[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.
The proposed network is the first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously ...
We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both generator and descriptor ends. ...
The error in disparity is given by L1 loss. We use wasserstein metric as GAN loss function for stable training using gradient descent [1] . ...
arXiv:1904.11163v1
fatcat:ztnbw3quxzcohoiqvx7dctml5i
ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Importantly, the proposed method enhances the robustness of the synthetic trained networks to the point that they outperform their fine-tuned counterparts (on real data) for challenging out-of-domain stereo ...
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. ...
The corresponding EPE is displayed on the estimated disparity map. ...
arXiv:2201.02263v2
fatcat:qdzmfql2mratzp3al43xl47sva
PLUMENet: Efficient 3D Object Detection from Stereo Images
[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
While many approaches rely on expensive 3D sensors such as LiDAR to produce accurate 3D estimates, methods that exploit stereo cameras have recently shown promising results at a lower cost. ...
Existing approaches tackle this problem in two steps: first depth estimation from stereo images is performed to produce a pseudo LiDAR point cloud, which is then used as input to a 3D object detector. ...
[15] proposes a new loss function based on the Wasserstein distance to further improve the depth prediction on object boundaries. b) LiDAR-based 3D Object Detection: LiDAR sensors capture high quality ...
arXiv:2101.06594v3
fatcat:spdwihruxney5omg23w54gszky
On the benefit of adversarial training for monocular depth estimation
2019
Computer Vision and Image Understanding
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
For the quality of the image reconstruction and disparity prediction, a combination of different losses is used, including L1 image reconstruction losses and left-right disparity smoothness. ...
A model can be trained in a self-supervised setting on stereo pairs of images, where depth (disparities) are an intermediate result in a right-to-left image reconstruction pipeline. ...
Acknowledgement This research was supported in part by the Dutch Organisation for Scientific Research, Netherlands via the VENI grant What & Where awarded to Dr. Mensink. ...
doi:10.1016/j.cviu.2019.102848
fatcat:pzycd5ynubfglbpcfhyji7c5lu
DDL-MVS: Depth Discontinuity Learning for MVS Networks
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our idea is to jointly estimate the depth and boundary maps where the boundary maps are explicitly used for further refinement of the depth maps. ...
Traditional MVS methods have good accuracy but struggle with completeness, while recently developed learning-based multi-view stereo (MVS) techniques have improved completeness except accuracy being compromised ...
The continuous disparity network [14] aims to regress the multi-modal depth by jointly estimating both probability and offset volume by minimizing a Wasserstein distance between the ground truth and ...
arXiv:2203.01391v2
fatcat:wkuqjxurdzdk3ajb4qyzhfzmeq
Towards Continual, Online, Self-Supervised Depth
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Effort has been made to make the proposed approach suitable for practical use. We apply our method to both structure-from-motion and stereo depth estimation. ...
Qualitative and quantitative results with both structure-from-motion and stereo show superior forgetting as well as adaptation performance compared to recent methods. ...
Wasserstein distance is used in [8] for depth estimation and 3D object detection. Authors in [9] propose a self-supervised scheme to estimate the depth and 3D scene flow simultaneously. ...
arXiv:2103.00369v3
fatcat:jhzpki73zvczdp5z2npw3xsbtu
Relativistic Approach for Training Self-supervised Adversarial Depth Prediction Model using Symmetric Consistency
2020
IEEE Access
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.
[15] viewed monocular depth estimation as a stereo matching problem. ...
They utilize the deep stereo matching network as a proxy to learn depth from synthetic data and provide dense supervision for training monocular depth estimation networks. ...
doi:10.1109/access.2020.3036893
fatcat:dhs6chiwvben3nwhqcahgvrtmy
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We first revisit the prior stereo detector DSGN for its stereo volume construction ways for representing both 3D geometry and semantics. ...
Second, for grasping differently spaced features, we present a novel stereo volume -- Dual-view Stereo Volume (DSV) that integrates front-view and top-view features and reconstructs sub-voxel depth in ...
CDN [67] further refine depth prediction near object boundarys via a Wasserstein distance-based loss. ...
arXiv:2204.03039v3
fatcat:scjsfynei5b3fbs3ewxmsimfgy
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector
[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-based 3D detection aims at detecting 3D object bounding boxes from stereo images using intermediate depth maps or implicit 3D geometry representations, which provides a low-cost solution for 3D ...
To solve the problem, we propose LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection ...
Wasserstein
In D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. distances for stereo disparity estimation. ...
arXiv:2108.08258v1
fatcat:hz7ix7azmfbf3oli7mpay7jf3a
Panchromatic Image Super-Resolution Via Self Attention-Augmented Wasserstein Generative Adversarial Network
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
features for detail enhancement. ...
To address this problem, an improved SR model which involves the self-attention augmented Wasserstein generative adversarial network ( SAA-WGAN) is designed to dig out the reference information among multiple ...
Wang created a parallax-attention mechanism (PASSRnet [16] ) to integrate the information from a stereo image pair, handling different stereo images with large disparity variations. ...
doi:10.3390/s21062158
pmid:33808682
fatcat:c5lbzf5jqrbwvck7dxub6dania
Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning
[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.
Recently, it was shown that one effective way to learn the priors for strongly scattering yet highly structured 3D objects, e.g. layered and Manhattan, is by a static neural network [Goy et al, Proc. ...
Even though training used NPCC as in (12) , we investigated two additional metrics for testing: probability of error (PE), the Wasserstein distance [82, 83] . ...
PE can be reduced to have a similar, but not equivalent, form to that of the Wasserstein distance. ...
arXiv:2007.10734v1
fatcat:kv37pc3vffcwbfyyzx2ycchkaq
« Previous
Showing results 1 — 15 out of 58 results