A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf
.
Filters
Energy-based Domain-Adaptive Segmentation with Depth Guidance
[article]
2024
arXiv
pre-print
Recent endeavors have been made to leverage self-supervised depth estimation as guidance in unsupervised domain adaptation (UDA) for semantic segmentation. ...
To address this issue, we propose a novel UDA framework called SMART (croSs doMain semAntic segmentation based on eneRgy esTimation) that utilizes Energy-Based Models (EBMs) to obtain task-adaptive features ...
Differently, we make the first attempt to achieve cross-domain semantic segmentation with depth guidance from an energy-based perspective. ...
arXiv:2402.03795v1
fatcat:wv6xbk5y2rcdlhqie437by5wyu
Perspective-aware warping for seamless stereoscopic image cloning
2012
ACM Transactions on Graphics
The perceived depth and projection of the pasted logo (b) are adjusted locally and adaptively to fit onto the bumpy surface. ...
The core of the proposed method is an iterative disparity adaptation process which alternates between two steps: disparity estimation, which re-estimates the disparities in the gradient domain so that ...
These cases are challenging for segmentation-based approaches. timated disparities. ...
doi:10.1145/2366145.2366201
fatcat:barrovflmvfuvlfg7jppmgs4qi
Surgical Audio Guidance: Feasibility Check for Robotic Surgery Procedures
2020
Current Directions in Biomedical Engineering
While the signal strength of the acoustic emissions decreases with distance from the point of interaction, an installation close to the patient would require sterilization measures. ...
To determine whether signals can be recorded at different potential mounting locations, instrument/tissue interactions with different textures were simulated in an experimental setup. ...
from three 1-second segments recorded during interaction with felt cloth (left), denim cloth (middle), liver (right). ...
doi:10.1515/cdbme-2020-3146
fatcat:dvzcadpg6bevfb3pfra5du23ya
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
[article]
2023
arXiv
pre-print
Furthermore, because the construction of the energy function is very flexible and adaptable to various conditions, our proposed FreeDoM has a broader range of applications than existing training-free methods ...
Experiments demonstrate that FreeDoM is effective for various conditions and suitable for diffusion models of diverse data domains, including image and latent code domains. ...
Recent works, such as Con-trolNet [49] and T2I-Adapter [28] , have introduced more training-required conditional interfaces to Stable Diffusion, such as edge maps, segmentation maps, depth maps, etc ...
arXiv:2303.09833v1
fatcat:7sgtxqyfmvcc7ot23r6afx5nyu
Image 3d Adaptive Algorithm Based on Graph Cut
2016
International Journal of Signal Processing, Image Processing and Pattern Recognition
Based on adaptive algorithm on the basis of in-depth study, this paper proposes a three-dimensional adaptation algorithm based on graph cut theory in order to realize the image matching. ...
Compared with the traditional algorithm, graph cut algorithm overall high precision and faster convergence speed in discontinuous area. ...
Conclusion Based on adaptive algorithm is made on the basis of in-depth study, put forward a kind of use of image segmentation based on graph cut theory of three-dimensional adaptive algorithm.Reference ...
doi:10.14257/ijsip.2016.9.8.30
fatcat:lcqpsqvojzfkxeega4y7clcuwa
Understanding Mystery Behind Example-Based Image Synthesis
[article]
2018
Eurographics State of the Art Reports
This tutorial presents a concise overview of development in the field of example-based image synthesis that over the last two decades rapidly evolved into a powerful tool enabling the production of synthetic ...
We will consider the heuristics used so far [JFA * 15, FJL * 16, FJS * 17] and compare them with alternatives, such as neural-based guidance [LYY * 17]. ...
Figure 2 : 2 Figure 2: An illustration of the guided synthesis principle [HJO * 01]: original photo (bottom left) is annotated with segmentation guide (top left), the user can then provide segmentation ...
doi:10.2312/egt.20181027
fatcat:pepelgjigjgynh4ghiwct77a54
Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
The domain adaption occurs in image space via 2D pixel-level guidance by Generative Adversarial Network (GAN) and 3D mesh guidance by mesh renderer (MR). ...
Via the domain adaption in image space, not only 3D HPE accuracy is improved, but also HOI input images are translated to segmented and de-occluded hand-only images. ...
Domain adaptation for HPE. ...
doi:10.1109/cvpr42600.2020.00616
dblp:conf/cvpr/BaekKK20
fatcat:ugakckgbsvbgzmr4u3o7fcgsba
Guided Depth Map Super-resolution: A Survey
[article]
2023
arXiv
pre-print
Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution (HR) depth map from a low-resolution (LR) observation with the help of a paired HR color image, is a longstanding and ...
In addition, we roughly classify existing GDSR methods into three categories, i.e., filtering-based methods, prior-based methods, and learning-based methods. ...
Dynamic filter SGF [148] CVPR-2015 Segments graph based filter that takes the tree distance calculated on the segment graph as guidance affinity. ...
arXiv:2302.09598v1
fatcat:36awga537vgf5fyyboba7rgcse
360^∘ Stereo Image Composition with Depth Adaption
[article]
2022
arXiv
pre-print
A deep depth densification network is proposed to generate depth guidance for the stereo image generation of each view segment according to the desired position and pose of the inserted object. ...
Therefore, we propose a novel view-dependent projection method that segments the object in 3D spherical space with the stereo camera pair facing in that direction. ...
(c) The stereo pair is generated with guidance from the densified depth maps for each view segment. ...
arXiv:2212.10062v1
fatcat:cvb6jrdut5barlpbmywtodx3tq
Time Segmented Image Fusion based Multi-depth Defects Imaging Method in Composites with pulsed terahertz
2020
IEEE Access
First, the surface reflection echo signal is removed by applying a time correction, and the time-domain signal is then segmented according to the thickness of the sample. ...
To solve this problem, a timedomain piecewise imaging method based on terahertz signal extraction is proposed in this article. ...
Pei in algorithm guidance. And thanks to engineer Linyu Liu and Xiansheng Zhang for guidance. ...
doi:10.1109/access.2020.3019319
fatcat:yfcfhr5uhbbr3le3trba5i5k2e
A Deep Primal-Dual Network for Guided Depth Super-Resolution
[article]
2016
arXiv
pre-print
Therefore, we generate high-quality depth maps and corresponding color images with a physically based renderer. ...
We combine a deep fully convolutional network with a non-local variational method in a deep primal-dual network. ...
Hence, we map a noisy, LR depth map along with a HR guidance image to an accurate HR estimate. ...
arXiv:1607.08569v1
fatcat:hqxhkgtjl5cplmpn2sqpdvfo3m
Creating Contents Based on Inter-play between the Ontologies of Content's Key Segments and Problem Context
2009
2009 Computation World: Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns
An approach is presented to show how contents can be created through an inter-play between the ontology of their key segments and the ontology of problem context using the knowledge on some nominal values ...
Also, with regard to the ontology of constraints, we are primarily concerned with the existing limitations/ restrictions with respect to issues such as time, space, energy, and resources, users,… that ...
can be applied to education or planning issues [19] , improving adaptive navigation with case-based reasoning [20] ,story plot generation based on CBR [21] ,knowledge intensive template selection using ...
doi:10.1109/computationworld.2009.15
fatcat:7ft44cxznvck3p6qta2fglnbzu
Guest Editorial: Special Section on Advanced Deep Learning Algorithms for Industrial Internet of Things
2021
IEEE Transactions on Industrial Informatics
fault diagnosis method based on an improved domain adaptation method with the help of deep learning algorithms. ...
For this problem, the article "An Adaptive Trust Boundary Protection for IIoT Networks Using Deep Learning Feature Extraction based Semi-Supervised Model" authored by Hassan et al. proposed an adaptive ...
doi:10.1109/tii.2020.3026551
fatcat:drpgvjt6gnafliu3ch7zxebn7y
Depth Completion using Piecewise Planar Model
[article]
2020
arXiv
pre-print
A depth map can be represented by a set of learned bases and can be efficiently solved in a closed form solution. ...
However, one issue with this method is that it may create artifacts when colour boundaries are inconsistent with depth boundaries. In fact, this is very common in a natural image. ...
Energy Minimization based depth inpainting methods [11, 12] take characteristics of depth maps as a regularization term in energy minimization and generate more plausible results. ...
arXiv:2012.03195v1
fatcat:jfpzqaav6bcenk5yj325vgu5gu
Task-specific Scene Structure Representations
[article]
2023
arXiv
pre-print
To do this, we first analyze traditional spectral clustering methods, which computes a set of eigenvectors to model a segmented graph forming small compact structures on image domains. ...
In this paper, we propose a single general neural network architecture for extracting task-specific structure guidance for scenes. ...
MMSR introduces a mutual modulation strategy with the cross-domain adaptive filtering and adopts a cycle consistency loss to train the model in a fully self-supervised manner. ...
arXiv:2301.00555v1
fatcat:2djujgfk3bcxno4afx4eizcsma
« Previous
Showing results 1 — 15 out of 30,123 results