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.
Filters
Spatial Sampling Network for Fast Scene Understanding
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Preserved Fulltext
We propose a network architecture to perform efficient scene understanding. ...
Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. ...
We gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan Xp GPU used for this research. ...
doi:10.1109/cvprw.2019.00168
dblp:conf/cvpr/MazziniS19
fatcat:m6wohnxilndu7dnwnpntd25b4q
PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
[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.
Instance segmentation of planar regions in indoor scenes benefits visual SLAM and other applications such as augmented reality (AR) where scene understanding is required. ...
We also utilize a Residual Feature Augmentation module in the Feature Pyramid Network (FPN). ...
INTRODUCTION Detection of 3D geometry features in scenes supports tasks such as 3D scene understanding, robot navigation and Simultaneous Localization and Mapping (SLAM). ...
arXiv:2103.15428v1
fatcat:l6cczxtxajh3voxt3oknmqdzsm
Real-time Semantic Segmentation with Fast Attention
[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.
Other Versions
Moreover, to efficiently process high-resolution input, we apply an additional spatial reduction to intermediate feature stages of the network with minimal loss in accuracy thanks to the use of the fast ...
The proposed architecture relies on our fast spatial attention, which is a simple yet efficient modification of the popular self-attention mechanism and captures the same rich spatial context at a small ...
FAST ATTENTION NETWORK In this section, we describe the Fast Attention Network (FANet) for real-time image semantic segmentation. ...
arXiv:2007.03815v2
fatcat:ldrnwzmwsjekvk7zki5b6wtv5m
Spatio-Temporal Context for Action Detection
[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.
Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task. ...
Research in action detection has grown in the recentyears, as it plays a key role in video understanding. ...
Backbone Network. The backbone is a SlowFast R50 with input sampling T ×τ = 8×8, without non local blocks and spatial resolution of res 5 increased by 2. ...
arXiv:2106.15171v1
fatcat:wukoutuwjvbnhonkf6py6t2e34
DSNet: An Efficient CNN for Road Scene 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 2020; you can also visit the original URL.
The file type is application/pdf.
Road scene understanding is a critical component in an autonomous driving system. ...
Although the deep learning-based road scene segmentation can achieve very high accuracy, its complexity is also very high for developing real-time applications. ...
We would like to thank Shao-Yuan Lo for his helpful discussions during the course of this project. ...
arXiv:1904.05022v1
fatcat:o3hhp2n7angg3kxjscos3g5c74
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
[article]
2016
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 achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. ...
We present a framework for efficient inference in structured image models that explicitly reason about objects. ...
The result is fast, feed-forward, interpretable scene understanding trained without supervision. ...
arXiv:1603.08575v3
fatcat:xouycxqk5jf57ce4bghtva3doa
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
2015
Proceedings of the 10th International Conference on Computer Vision Theory and Applications
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 2016; you can also visit the original URL.
The file type is application/pdf.
We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. ...
Classifying single image patches is important in many different applications, such as road detection or scene understanding. ...
Urban scene understanding For urban scene understanding, each pixel is classified into one of K classes. ...
doi:10.5220/0005355105100517
dblp:conf/visapp/BrustSSRD15
fatcat:hmkpme6d55emljdoy4m2bcmlaa
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
[article]
2015
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.
We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. ...
Classifying single image patches is important in many different applications, such as road detection or scene understanding. ...
Urban scene understanding For urban scene understanding, each pixel is classified into one of K classes. ...
arXiv:1502.06344v1
fatcat:y2so3iwhwfe75h43cjsmbhlmyy
Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs
[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
To address these challenges, we begin by analyzing visibility statistics for large-scale scenes, motivating a sparse network structure where parameters are specialized to different regions of the scene ...
, each of which capture only a small subset of the scene, (2) prohibitively large model capacities that make it infeasible to train on a single GPU, and (3) significant challenges for fast rendering that ...
Acknowledgments This research was supported by the National Science Foundation (NSF) under grant number CNS-2106862, the Defense Science and Technology Agency of Singapore (DSTA), and the CMU Argo AI Center for ...
arXiv:2112.10703v2
fatcat:zdiiudegzvewjhmc2unvhhiukm
DSNet: an efficient CNN for road scene segmentation
2020
APSIPA Transactions on Signal and Information Processing
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.
Road scene understanding is a critical component in an autonomous driving system. ...
Although the deep learning-based road scene segmentation can achieve very high accuracy, its complexity is also very high for developing real-time applications. ...
The second dataset is Cityscapes [19] , which is a larger dataset for semantic understanding of urban street scenes. All images are at 2048 × 1024 resolution and there are 19 classes for training. ...
doi:10.1017/atsip.2020.25
fatcat:7rlk6gqk3jhhdkt3ik35ip5st4
Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models
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.
Abstract We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models. ...
Our method operates on a top-down image-based representation, and inserts objects iteratively into the scene by predicting their category, location, orientation and size with separate neural network modules ...
Acknowledgments We thank the anonymous reviewers for their helpful suggestions. Scene renderings shown in this paper were created using the Mitsuba physically-based renderer [12] . ...
doi:10.1109/cvpr.2019.00634
dblp:conf/cvpr/Ritchie0L19
fatcat:yze6miopsbga3g3xaj7lwf4xa4
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric 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.
We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. ...
For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects. ...
The neural network is trained extensively calculating the similarity for pairs of sampled pixels. ...
arXiv:2007.03169v1
fatcat:cms4hzgwjnf6hkqaeclr4eln6y
CP-SSD: Context Information Scene Perception Object Detection Based on SSD
2019
Applied Sciences
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.
CP-SSD promotes the network's understanding of context information by using context information scene perception modules, so as to capture context information for objects of different scales. ...
In order to alleviate these problems, we propose a single-shot object detection network Context Perception-SSD (CP-SSD). ...
ability to understand the scene. ...
doi:10.3390/app9142785
fatcat:6ly7erl53belbkwumoezqoxf6u
Real-time Semantic Segmentation with Context Aggregation Network
[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 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.00993v1 fatcat:iwpdpdgsavclrmzqzw7clanr64
With the increasing demand of autonomous systems, pixelwise semantic segmentation for visual scene understanding needs to be not only accurate but also efficient for potential real-time applications. ...
Building upon the existing dual branch architectures for high-speed semantic segmentation, we design a cheap high resolution branch for effective spatial detailing and a context branch with light-weight ...
[21] developed an approach which exploits light-weight upsampling and lateral connections with a residual network as the main recognition engine for real-time scene understanding. ...
arXiv:2011.00993v2
fatcat:qftm2mwbubhi3bgh5si34f5vza
Fast Light Field Reconstruction with Deep Coarse-to-Fine Modeling of Spatial-Angular Clues
[chapter]
2018
Lecture Notes in Computer Science
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.
In this paper, we propose a learning based algorithm to reconstruct a densely-sampled LF fast and accurately from a sparsely-sampled LF in one forward pass. ...
Specifically, our end-to-end model first synthesizes a set of intermediate novel sub-aperture images (SAIs) by exploring the coarse characteristics of the sparsely-sampled LF input with spatial-angular ...
In this paper, we propose a novel learning based model for fast reconstruction of a densely-sampled LF from a very sparsely-sampled LF. ...
doi:10.1007/978-3-030-01231-1_9
fatcat:fe7cg5sv3jfcrj54avrylhwvjq
« Previous
Showing results 1 — 15 out of 32,664 results