• Corpus ID: 168169786

Flat2Layout: Flat Representation for Estimating Layout of General Room Types

  title={Flat2Layout: Flat Representation for Estimating Layout of General Room Types},
  author={Chi-Wei Hsiao and Cheng Sun and Min Sun and Hwann-Tzong Chen},
This paper proposes a new approach, Flat2Layout, for estimating general indoor room layout from a single-view RGB image whereas existing methods can only produce layout topologies captured from the box-shaped room. [] Key Method A dynamic programming based postprocessing is employed to decode the estimated flat output from the deep model into the final room layout. Flat2Layout achieves state-of-the-art performance on existing room layout benchmark. This paper also constructs a benchmark for validating the…

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

This work proposes to incorporate geometric reasoning to deep learning for layout estimation and presents a new dataset with pixel-level depth annotation of dominant planes, which is larger than the existing datasets and contains both cuboid and non-cuboid rooms.

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

This approach learns an additional ranking function to estimate the final layout of a room from its single image and proposes a framework to train a CNN using max-margin structure cost.

Efficient Small-Scale Network for Room Layout Estimation

This work presents a more lightweight solution to retrieving the layout of different cluttered indoor scenes from monocular images, running the segmentation on a smaller neural network and introducing a discriminative classifier for the posterior layout ranking and optimization.

LayART: Generating indoor layout using ARCore Transformations

This work takes advantage of Simultaneous Localization and Mapping (SLAM) to assess the 3D transformations required for layout generation and proposed generation of layout using an RGB image captured using a simple mobile phone camera is fast and efficient.

360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation

360-DFPE is presented, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information, and proposes a novel room identification algorithm that tracks every room along the camera exploration using geometry information.

Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes

The proposed Scan2Plan method incorporates a two-stage approach where the initial stage clusters an unordered point cloud representation of the scene into room instances and wall instances using a deep neural network based voting approach.

3D Room Layout Recovery Generalizing across Manhattan and Non-Manhattan Worlds

Recent 3D room layout recovery approaches mostly concentrate on Manhattan layouts, where the vertical walls are orthogonal with respect to each other, even though there are many rooms with

GRIHA: synthesizing 2-dimensional building layouts from images captured using a smart phone

This work proposes a framework named GRIHA (Generating Room Interior of a House using ARcore), which takes advantage of RGB images taken from a conventional mobile phone camera, and uses SLAM based Google ARcore library for camera pose estimation while capturing the images.

A Review of Techniques for 3D Reconstruction of Indoor Environments

This paper reviews the state-of-the-art techniques for the three-dimensional (3D) reconstruction of indoor environments and concludes that most of the existing indoor environment reconstruction methods are based on the strong Manhattan assumption, which may not be true in a real indoor environment, hence limiting the effectiveness and robustness of existing indoor environments reconstruction methods.



LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image

An algorithm to predict room layout from a single image that generalizes across panoramas and perspective images, cuboid layouts and more general layouts (e.g. "L"-shape room) is proposed, which achieves among the best accuracy for perspective images and can handle both cuboid-shaped and moregeneral Manhattan layouts.

RoomNet: End-to-End Room Layout Estimation

This paper predicts the locations of the room layout keypoints using RoomNet, an end-to-end trainable encoder-decoder network and presents optional extensions to the RoomNet architecture such as including recurrent computations and memory units to refine the keypoint locations under the same parametric capacity.

Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment

This paper presents an encoder–decoder network with shared encoder and two separate decoders, which are composed of multiple deconvolution (transposed convolution) layers, to jointly learn the edge maps and semantic labels of a room image and applies a novel refinement strategy to further optimize the layout hypotheses.

HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation

The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches and can diversify panorama data and be applied to other panorama-related learning tasks.

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method

This work adopts a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally and forms an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement.

DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes

This paper presents a method that uses a fully convolutional neural network (FCNN) in conjunction with a novel optimization framework for generating layout estimates, and demonstrates that it is robust in the presence of clutter and handles a wide range of highly challenging scenes.

Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction

A novel method to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction and experimentally verify the proposed method with the publicly available synthetic and real-world datasets.

Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation

An alternative method to estimate room layouts of cluttered indoor scenes by developing a principled and efficient inference scheme named physics inspired optimization (PIO), which is to formulate some phenomena observed in semantic transfer features into mechanics concepts.

DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama

A deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama that leverages two projections of the panorama at once, namely the equirectangular panorama-view and the perspective ceiling-view, that each contains different clues about the room layouts.

Recovering the spatial layout of cluttered rooms

This paper introduces a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues, and gains robustness to clutter by modeling the global room space with a parameteric 3D “box” and by iteratively localizing clutter and refitting the box.