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

Howard-Jenkins, Henry; Li, Shuda; Prisacariu, Victor Adrian

doi:10.1007/978-3-030-20887-5_27

Cited by 12 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works addressed generic room layouts prediction in the past. But they either assumed camera model exists in the data and used camera pose in their approaches [11,27] or conducted their prediction work on panoramic views [3,37,23]. The only work we found has a similar problem setup as us is [12], however we could not find the code of their approach online.…”

Section: Results On Generic Room Imagesmentioning

confidence: 93%

“…The work in [12] uses a representation to detect non-cuboidal layouts which estimates the probability of wall-wall boundary locations and corners in a reprojected the image and uses it to sample layouts. Similarly, [27,11] uses planes estimated by analyzing RGB or RGBD images to sample non-cuboidal layouts. In contrast to these works, our model explicitly outputs generic layout parameters such as number of visible walls and corners, instead of just sampling non-cuboidal layouts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View

Zhang,

Wang,

Deng

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we present a new approach to estimate the layout of a room from its single image. While recent approaches for this task use robust features learnt from data, they resort to optimization for detecting the final layout. In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final layout instead of using optimization. To learn this ranking function, we propose a framework to train a CNN using max-margin structure cost. Also, while most approaches aim at detecting cuboidal layouts, our approach detects non-cuboidal layouts for which we explicitly estimates layout complexity parameters. We use these parameters to propose layout candidates in a novel way. Our approach shows state-of-the-art results on standard datasets with mostly cuboidal layouts and also performs well on a dataset containing rooms with non-cuboidal layouts.

show abstract

Section: Results On Generic Room Imagesmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View

Zhang,

Wang,

Deng

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We focus here on the creation of a structured floor plan where each room of an indoor environment is represented as a polygon with one edge per wall. Many types of input have been considered: Monocular perspective color views [18,19,22,31], panoramic views [32,38,40], depth…”

Section: Introductionmentioning

confidence: 99%

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

Stekovic

Rad

Fraundorfer

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We propose a novel method for reconstructing floor plans from noisy 3D point clouds. Our main contribution is a principled approach that relies on the Monte Carlo Tree Search (MCTS) algorithm to maximize a suitable objective function efficiently despite the complexity of the problem. Like previous work, we first project the input point cloud to a top view to create a density map and extract room proposals from it. Our method selects and optimizes the polygonal shapes of these room proposals jointly to fit the density map and outputs an accurate vectorized floor map even for large complex scenes. To do this, we adapt MCTS, an algorithm originally designed to learn to play games, to select the room proposals by maximizing an objective function combining the fitness with the density map as predicted by a deep network and regularizing terms on the room shapes. We also introduce a refinement step to MCTS that adjusts the shape of the room proposals. For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals. We evaluate our method on the recent and challenging Structured3D and Floor-SP datasets and show a significant improvement over the state-of-theart, without imposing any hard constraints nor assumptions on the floor plan configurations.

show abstract

“…Recent approaches [6,25] attempt to relax these assumptions by casting room layout estimation as a plane detection problem. For example, Planar R-CNN [6] modifies Faster R-CNN [19] to detects 3D planes and Render-and-Compare (in short, RaC) [25] builds upon the advanced plane detection method PlaneRCNN [13]. To correctly infer room layout with relaxed assumptions, two core challenges must be addressed properly.…”

Section: Introductionmentioning

confidence: 99%

“…One challenge is how to infer the connectivity relations between planes in 3D space. Planar R-CNN [6] does not reason such relation and only reconstructs the piece-wise planar surfaces. RaC [25] defines a constrained discrete optimization problem to reason the relations.…”

Section: Introductionmentioning

confidence: 99%