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.
Filters
Progressive 3D Scene Understanding with Stacked Neural Networks
2018
Pacific Conference on Computer Graphics and Applications
Preserved Fulltext
The scene understanding task is decomposed into several different but related tasks, and semantic objects are progressively separated from coarse to fine. ...
The former network segments the 3D scene at a coarser level and passes the result as context to the latter one for a finer-grained segmentation. ...
Inspired by this coarse-to-fine understanding process, we can use several networks to segment 3D scene progressively with refined semantic classes for 3D scene understanding task. ...
doi:10.2312/pg.20181280
dblp:conf/pg/SongS18
fatcat:vknckdkmiber3fmij4wvc7ikcq
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
[article]
2017
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 segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. ...
We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. ...
There are 37 indoor scene classes with corresponding segmentation labels (background is not considered as a class and is ignored during training and testing). ...
arXiv:1703.00551v1
fatcat:4xupd6go7ff6xdoxhk5awbgmjy
Semantic Bottleneck Scene Generation
[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.
For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts. ...
We assume pixel-wise segmentation labels are available during training and use them to learn the scene structure. ...
We thank Marvin Ritter for help with issues related to the compare gan library [27] . We are grateful to the members of BAIR for fruitful discussions. ...
arXiv:1911.11357v1
fatcat:id7o6lwt6bejfcs2tlnxt2rrb4
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
[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
Combined with a new 3D sparse generative neural network architecture, our method is able to predict highly-detailed surfaces in a coarse-to-fine hierarchical fashion, generating 3D scenes at 2cm resolution ...
To achieve self-supervision, we remove frames from a given (incomplete) 3D scan in order to make it even more incomplete; self-supervision is then formulated by correlating the two levels of partialness ...
Our self-supervision approach using loss masking enables more complete scene prediction than direct supervision using the target RGB-D scan, particularly in regions where occlusions commonly occur. ...
arXiv:1912.00036v2
fatcat:icywwuxxqjbuze2bxe6xbwnysy
Line Segment Detection Using Transformers without Edges
[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
We equip Transformers with a multi-scale encoder/decoder strategy to perform fine-grained line segment detection under a direct endpoint distance loss. ...
This loss term is particularly suitable for detecting geometric structures such as line segments that are not conveniently represented by the standard bounding box representations. ...
For each row, we show how a same line entity predicts line segments with same property in three different indoor/outdoor scenes. ...
arXiv:2101.01909v2
fatcat:keli33ufurdq7l2opoywlowjxa
Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes
[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
To alleviate this issue, we propose a novel deep graph convolutional network-based framework for large-scale semantic scene segmentation in point clouds with sole 2D supervision. ...
The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. ...
Then the following two Unets, CoarseNet and RefineNet, are used to generate the coarse-to-fine RGB images. Novel views can also be generated by taking the virtual tours for the total scene. ...
arXiv:2004.12498v2
fatcat:5mr6uuli6baixai7bjud24heda
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
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 2022; you can also visit the original URL.
The file type is application/pdf.
Key to our approach is its self-supervised formulation, enabling training solely on real-world, incomplete scans. ...
This not only obviates the need for synthetic ground truth, but is also capable of generating more complete scenes than any single target scene seen during training. ...
Our self-supervision approach using loss masking enables more complete scene prediction than direct supervision using the target RGB-D scan, particularly in regions where occlusions commonly occur. ...
doi:10.1109/cvpr42600.2020.00093
dblp:conf/cvpr/DaiDN20
fatcat:pmczslqzwng6vgcjik74r7dcne
The Reasonable Effectiveness of Synthetic Visual Data
2018
International Journal of Computer Vision
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.
Therefore, to tackle more challenging tasks, such as video scene understanding, progress is needed not only on the algorithmic and hardware fronts but also on the data front, both for learning and quantitative ...
The recent successes in many visual recognition tasks, such as image classification, object detection, and semantic segmentation can be attributed in large part to three factors: (i) advances in end-to-end ...
It is shown experimentally that the proposed coarse-to-fine approach can achieve millimetric relative localization without a single real-world training image. • In "3D interpreter networks for viewer-centered ...
doi:10.1007/s11263-018-1108-0
fatcat:53z6bysvyvgclmz3ywxohlxqca
3D Semantic Scene Completion: a Survey
[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
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. ...
Specifically, SSC lies in the ambiguous completion of large unobserved areas and the weak supervision signal of the ground truth. ...
Coarse-to-fine (b), similarly to multi-scale relies on multiple size predictions, but trains in a multi-stage coarse to fine manner. ...
arXiv:2103.07466v3
fatcat:swz4azlznre3laziatls6sdrfm
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
[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 2020; you can also visit the original URL.
The file type is application/pdf.
We first propose a network architecture called Label Refinement Network (LRN) that predicts segmentation labels in a coarse-to-fine fashion at several spatial resolutions. ...
Initially, G-FRNet makes a coarse-grained prediction which it progressively refines to recover details by effectively integrating local and global contextual information during the refinement stages. ...
Our model produces segmentation labels in a coarse-to-fine manner. The segmentation labels at coarse levels are used to progressively refine the labeling produced at finer levels. ...
arXiv:1806.11266v1
fatcat:nzfn3zaxvvbe7ajtxuztzb5a2y
Monocular spherical depth estimation with explicitly connected weak layout cues
2022
ISPRS journal of photogrammetry and remote sensing (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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2206.11358v1 fatcat:vksdzyphbrc6vajiw5f2lkqypu
Recently, with the availability of appropriate datasets, there has also been progress in depth estimation from a single omnidirectional image. ...
Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation. ...
Multi-scale Supervision We supervise both tasks, with the estimated depth maps being supervised in three scales s ∈ {0, 1, 2} from coarse to fine, resulting in the following combined loss function: L = ...
doi:10.1016/j.isprsjprs.2021.10.016
fatcat:zoz6hrijybejtfzhmpkqcxksvu
Semantic Foggy Scene Understanding with Synthetic Data
2018
International Journal of Computer Vision
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:
2017 pre-print arXiv:1708.07819v2 fatcat:dqedeu7365b5tcld7hnkrgd5uiOther Versions
For evaluation, we present Foggy Driving, a dataset with 101 real-world images depicting foggy driving scenes, which come with ground truth annotations for semantic segmentation and object detection. ...
Extensive experiments show that 1) supervised learning with our synthetic data significantly improves the performance of state-of-the-art CNN for SFSU on Foggy Driving; 2) our semi-supervised learning ...
Acknowledgements The authors would like to thank Kevis Maninis for useful discussions. This work is funded by Toyota Motor Europe via the research project TRACE-Zürich. ...
doi:10.1007/s11263-018-1072-8
fatcat:anr5t3jyfrewlkcszwor6a6zyq
Multi-scale iterative refinement network for RGB-D salient object detection
2021
Engineering applications of artificial 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 2022; 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:
2022 pre-print arXiv:2201.09574v1 fatcat:hvh6cmdwvvbuxf6s7bpfod6cte
In this paper, we begin by introducing top-down and bottom-up iterative refinement architecture to leverage multi-scale features, and then devise attention based fusion module (ABF) to address on cross-modal ...
However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels. ...
We use iterative refinement to progressively refine the salient maps reinforced by coarseto-fine supervision. ...
doi:10.1016/j.engappai.2021.104473
fatcat:2dj6azts2fajlju7c55mnpw5sq
RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
[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.
Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. ...
We consider RIO a particularly important task in 3D vision since it enables a wide range of practical applications, including AI-assistants or robots that are asked to find a specific object in a 3D scene ...
Acknowledgment We would like to thank the volunteers who helped with 3D scanning, all expert annotators, as well as Jürgen Sturm, Tom Funkhouser and Maciej Halber for fruitful discussions. ...
arXiv:1908.06109v1
fatcat:wzcalwtmffhjrmmbjwlc3v4ubi
Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation
[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.
For the point branch, we use Multi-Layer Perceptron (MLP) to extract fine-detailed point-wise features. Outputs from these two branches are adaptively fused via a feature selection module. ...
We evaluate our method on popular point cloud datasets for object classification and semantic segmentation tasks. ...
Indoor Scene Segmentation Data and Implementation Details We conduct experiments on S3DIS [1] for large-scale indoor scene segmentation. ...
arXiv:2109.11614v1
fatcat:lyw4o4qgrrgfhf4n2hiq35i7ky
« Previous
Showing results 1 — 15 out of 1,341 results