Double Refinement Network for Room Layout Estimation

Kruzhilov, Ivan; Romanov, Mikhail; Babichev, Dmitriy A.; Konushin, Anton

doi:10.1007/978-3-030-41404-7_39

Cited by 10 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, our method has reached the level of state-of-the-art two-step method of Double Refinement [13] in KE.…”

Section: Testing Resultsmentioning

confidence: 88%

“…The two-step methods usually follow the proposal-ranking scheme, in which the whole process, from feature extraction to proposal ranking is processed by a human-designed program [4][5][6][7][8]. As the rise of deep learning, some two-step methods use neural networks for feature extraction with great improvements in accuracy [9][10][11][12][13]. In general, these methods use an additional post-processing step to elevate the results' precision but require a much longer processing time and more manually participating than that of the endto-end methods.…”

Section: Two-step Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Toward Enhancing Room Layout Estimation by Feature Pyramid Networks

et al. 2022

View full text Add to dashboard Cite

As a fundamental part of indoor scene understanding, the research of indoor room layout estimation has attracted much attention recently. The task is to predict the structure of a room from a single image. In this paper, we illustrate that this task can be well solved even without sophisticated post-processing program, by adopting Feature Pyramid Networks (FPN) to solve this problem with adaptive changes. The proposed model employs two strategies to deliver quality output. First, it can predicts the coarse positions of key points correctly by preserving the order of these key points in the data augmentation stage. Then the coordinate of each corner point is refined by moving each corner point to its nearest image boundary as output. Our method has demonstrated great performance on the benchmark LSUN dataset on both processing efficiency and accuracy. Compared with the state-of-the-art end-to-end method, our method is two times faster at processing speed (32 ms) than its speed (86 ms), with 0.71% lower key point error and 0.2% higher pixel error respectively. Besides, the advanced two-step method is only 0.02% better than our result on key point error. Both the high efficiency and accuracy make our method a good choice for some real-time room layout estimation tasks.

show abstract

“…In fact, our method has reached the level of state-of-the-art two-step method of Double Refinement [13] in KE.…”

Section: Testing Resultsmentioning

confidence: 88%

Section: Two-step Methodsmentioning

confidence: 99%

Toward Enhancing Room Layout Estimation by Feature Pyramid Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…DeepRoom3D [14] use an endto-end CNN to predict a cuboid and RoomNet [12] directly predicts ordered keypoints in a room layout. A group of recent methods [20,34,28,10] use CNNs to predict edges and then optimize for the Room Layout using geometric priors.…”

Section: Related Workmentioning

confidence: 99%

“…For example Lin et al [13] predict a semantic segmentation which is later used to optimize intersection lines heuristically. Other methods [20,34,28,10] predict edges and then optimize. The most recent work of [29] use a combination of plane, depth and vertical line detections to heuristically fuse and generate a Room Layout.…”

Section: Introductionmentioning

confidence: 99%

Semantic Room Wireframe Detection from a Single View

Gillsjö

Flood

Åström

2022

2022 26th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

This paper presents a neural network based semantic plane detection method utilizing polygon representations. The method can for example be used to solve room layout estimations tasks. The method is built on, combines and further develops several different modules from previous research. The network takes an RGB image and estimates a wireframe as well as a feature space using an hourglass backbone. From these, line and junction features are sampled. The lines and junctions are then represented as an undirected graph, from which polygon representations of the sought planes are obtained. Two different methods for this last step are investigated, where the most promising method is built on a heterogeneous graph transformer. The final output is in all cases a projection of the semantic planes in 2D. The methods are evaluated on the Structured 3D dataset and we investigate the performance both using sampled and estimated wireframes. The experiments show the potential of the graph-based method by outperforming state of the art methods in Room Layout estimation in the 2D metrics using synthetic wireframe detections.

show abstract

GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes

Zhang

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The task of room layout estimation is to locate the wallfloor, wall-ceiling, and wall-wall boundaries. Most recent methods solve this problem based on edge/keypoint detection or semantic segmentation. However, these approaches have shown limited attention on the geometry of the dominant planes and the intersection between them, which has significant impact on room layout. In this work, we propose to incorporate geometric reasoning to deep learning for layout estimation. Our approach learns to infer the depth maps of the dominant planes in the scene by predicting the pixel-level surface parameters, and the layout can be generated by the intersection of the depth maps. Moreover, we present a new dataset with pixel-level depth annotation of dominant planes. It is larger than the existing datasets and contains both cuboid and non-cuboid rooms. Experimental results show that our approach produces considerable performance gains on both 2D and 3D datasets.

show abstract

Double Refinement Network for Room Layout Estimation

Cited by 10 publications

References 23 publications

Toward Enhancing Room Layout Estimation by Feature Pyramid Networks

Toward Enhancing Room Layout Estimation by Feature Pyramid Networks

Semantic Room Wireframe Detection from a Single View

GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes

Contact Info

Product

Resources

About