RoomNet: End-to-End Room Layout Estimation

Lee, Chen‐Yu; Badrinarayanan, Vijay; Malisiewicz, Tomasz; Rabinovich, Andrew

doi:10.1109/iccv.2017.521

Cited by 158 publications

(136 citation statements)

References 40 publications

(68 reference statements)

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…As can be seen with the results presented in Table 3, we outperform all RGB methods tested, including PlaneNet [19] and RoomNet [18], designed for this task. We also believe our results could be improved by merging architectural plane detections if the plane equations are similar.…”

Section: D Room Layout Predictionssupporting

confidence: 58%

“…The eleven possible representations of the box model room in 2D, as defined in [35], have lead to the problem being formulated as a segmentation problem with classes each representing separate instances of the bounding surfaces: left wall, middle wall, right wall, floor and ceiling as in [7]. Furthermore, the eleven representations have been leveraged to tackle layout estimation as an ordered keypoint detection and classification problem as in [18], where the room type and the type's respective labelled corners are inferred directly from the image. These 2D representations have been used to produce 3D geometry by informing and ranking room hypotheses [15].…”

Section: Cloudmentioning

confidence: 99%

See 1 more Smart Citation

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

Howard-Jenkins

Prisacariu

2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference problem as an instance detection task, which we solve by directly regressing 3D planes using an R-CNN. We then use a variant of probabilistic clustering to combine the 3D planes regressed at each frame in a video sequence, with their respective camera poses, into a single global 3D room layout estimate. Finally, we showcase results which make no assumptions about perpendicular alignment, so can deal effectively with walls in any alignment.

show abstract

Section: D Room Layout Predictionssupporting

confidence: 58%

Section: Cloudmentioning

confidence: 99%

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

Howard-Jenkins

Prisacariu

2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

show abstract

“…Recently, there are several other works [22,9,24,21,18] related to room layouts, but they focus on a different problem, i.e., to reconstruct 3D room layouts from photos.…”

Section: Related Workmentioning

confidence: 99%

Deep Floor Plan Recognition Using a Multi-Task Network With Room-Boundary-Guided Attention

Zeng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

This paper presents a new approach to recognize elements in floor plan layouts. Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts. To this end, we model a hierarchy of floor plan elements and design a deep multi-task neural network with two tasks: one to learn to predict room-boundary elements, and the other to predict rooms with types. More importantly, we formulate the room-boundary-guided attention mechanism in our spatial contextual module to carefully take room-boundary features into account to enhance the room-type predictions. Furthermore, we design a cross-and-within-task weighted loss to balance the multi-label tasks and prepare two new datasets for floor plan recognition. Experimental results demonstrate the superiority and effectiveness of our network over the state-of-the-art methods.

show abstract

“…Single-view Scene Modeling Indoor scene modeling from RGB images can be divided into two branches: 1. layout prediction and 2. indoor content modeling. Based on the Manhattan assumption [26], layout prediction represents indoor layout with cuboid proposals using line segments [27] or CNN feature maps [14,10].…”

Section: Related Workmentioning

confidence: 99%

“…the location of the floor, ceiling and walls). Using CNNs to produce layout features, current works [14,10] generally ask for camera parameters to estimate vanishing points for layout proposal decision. We adopt the Fully Convolutional Network (FCN) from [14] to extract the layout edge map and label map.…”

Section: Non-relational Semantics Parsingmentioning

confidence: 99%

Shallow2Deep: Indoor scene modeling by single image understanding

Nie

Guo

Chang

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a single RGB image, our method simultaneously recovers semantic contents, 3D geometry and object relationship by reasoning indoor environment context. Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling. It involves multi-level convolutional networks to parse indoor semantics/geometry into non-relational and relational knowledge. Non-relational knowledge extracted from shallow-end networks (e.g. room layout, object geometry) is fed forward into deeper levels to parse relational semantics (e.g. support relationship). A Relation Network is proposed to infer the support relationship between objects. All the structured semantics and geometry above are assembled to guide a global optimization for 3D scene modeling. Qualitative and quantitative analysis demonstrates the feasibility of our method in understanding and modeling semantics-enriched indoor scenes by evaluating the performance of reconstruction accuracy, computation performance and scene complexity. Shallow2Deep: Indoor Scene Modeling by Single Image Understanding vision tasks [1] and most of them are still under active development, e.g. object segmentation [2], layout estimation [3] and geometric reasoning [4]. Although machine intelligence has reached comparable human-level performance in some tasks (e.g. scene recognition [5]), those techniques are only able to represent a fragment knowledge of full scene context.With the lack of depth clues, prior studies reconstructed indoor scenes from a single image by exploiting shallow image features (e.g. line segments and HOG descriptors [6,4]) or introducing depth estimation [7,8] to search object models. Other works adopt Render-and-Match strategy to obtain CAD scenes with their renderings similar as input images [9]. However, it is still an unresolved problem when indoor geometry is over-cluttered and complicated. The reasons are threefold. First, complicated indoor scenes involve heavily occluded objects, which could cause missing contents in detection [9]. Second, cluttered environments significantly increase the difficulty of camera and layout estimations, which critically affects the reconstruction quality [10]. Third, compared to the large diversity of objects in real scenes, the reconstructed virtual environment is still far from satisfactory (missing small pieces, wrong labeling). Existing methods have explored the use of various contextual knowledge, including object support relationship [7,8] and human activity [7], to improve modeling quality. However, their relational (or contextual) features are hand-crafted and would fail to cover a wide range of objects in cluttered scenes.

show abstract

RoomNet: End-to-End Room Layout Estimation

Cited by 158 publications

References 40 publications

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

Deep Floor Plan Recognition Using a Multi-Task Network With Room-Boundary-Guided Attention

Shallow2Deep: Indoor scene modeling by single image understanding

Contact Info

Product

Resources

About