Double Refinement Network for Room Layout Estimation

Kruzhilov, Ivan; Romanov, Mikhail; Konushin, Anton

doi:10.20944/preprints201905.0270.v1

Cited by 4 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, there is also a large body of work that estimates floorplans for indoor environments from single images [22,26], sequences [34], or 3D data [25,17,24]. While related, these methods are mostly concerned with estimating the shape of rooms, ignoring 'things,' e.g.…”

Section: Related Workmentioning

confidence: 99%

Heightfields for Efficient Scene Reconstruction for AR

Watson¹,

Vicente²,

Aodha

et al. 2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

3D scene reconstruction from a sequence of posed RGB images is a cornerstone task for computer vision and augmented reality (AR). While depth-based fusion is the foundation of most real-time approaches for 3D reconstruction, recent learning based methods that operate directly on RGB images can achieve higher quality reconstructions, but at the cost of increased runtime and memory requirements, making them unsuitable for AR applications. We propose an efficient learning-based method that refines the 3D reconstruction obtained by a traditional fusion approach. By leveraging a top-down heightfield representation, our method remains real-time while approaching the quality of other learning-based methods. Despite being a simplification, our heightfield is perfectly appropriate for robotic path planning or augmented reality character placement. We outline several innovations that push the performance beyond existing top-down prediction baselines, and we present an evaluation framework on the challenging ScanNetV2 dataset, targeting AR tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Heightfields for Efficient Scene Reconstruction for AR

Watson¹,

Vicente²,

Aodha

et al. 2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…RoomNet [11] directly predicts ordered keypoints in a room layout and DeepRoom3D [12] use an end-to-end CNN to predict a cuboid. Most recent methods [13]- [16] use CNNs to predict edges and then optimize for the Room Layout using geometric priors. The datasets mostly used are LSUN [17] and Hedau [5].…”

Section: Related Workmentioning

confidence: 99%

Semantic Room Wireframe Detection from a Single View

Gillsjö¹,

Flood²,

Åström³

2022

Preprint

View full text Add to dashboard Cite

Fig. 1. The images on top show the desired results from Semantic Room Wireframe detection and below are the results from a Room Layout estimation algorithm [1]. Lines are added between all detected planes for comparison.The algorithm produces satisfying results on simple scenes (left) but is lacking on more complex scenes, e.g. to the right where the wide opening is erroneously classified as part of the wall.

show abstract

“…Zou et al [95] proposed a method based directly on a panoramic image to predict cuboid and more general layout through a combination of multiple layout elements (e.g., corners and boundaries). Kruzhilov et al [103] combined keypoint maps and edge maps to predict the room layout using a double refinement network.…”

Section: Room Layout Estimationmentioning

confidence: 99%

“…The major limitation in the existing methods is generally related to the strong Manhattan assumption [92,94,96,97,[102][103][104]109], where the main structures of buildings are assumed to be rectangular and to intersect orthogonally. However, indoor spaces with complex geometric structures (e.g., cylindrical walls, spherical ceilings, L-shaped layout, or other non-planar structures [20,95,[165][166][167]) occur in current indoor environments.…”

Section: Non-manhattan Assumptionmentioning

confidence: 99%

A Review of Techniques for 3D Reconstruction of Indoor Environments

Zhang

Yang

Zhou

et al. 2020

IJGI

124

View full text Add to dashboard Cite

Indoor environment model reconstruction has emerged as a significant and challenging task in terms of the provision of a semantically rich and geometrically accurate indoor model. Recently, there has been an increasing amount of research related to indoor environment reconstruction. Therefore, this paper reviews the state-of-the-art techniques for the three-dimensional (3D) reconstruction of indoor environments. First, some of the available benchmark datasets for 3D reconstruction of indoor environments are described and discussed. Then, data collection of 3D indoor spaces is briefly summarized. Furthermore, an overview of the geometric, semantic, and topological reconstruction of the indoor environment is presented, where the existing methodologies, advantages, and disadvantages of these three reconstruction types are analyzed and summarized. Finally, future research directions, including technique challenges and trends, are discussed for the purpose of promoting future research interest. It can be concluded 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 environment reconstruction methods. Moreover, based on the hierarchical pyramid structures and the learnable parameters of deep-learning architectures, multi-task collaborative schemes to share parameters and to jointly optimize each other using redundant and complementary information from different perspectives show their potential for the 3D reconstruction of indoor environments. Furthermore, indoor–outdoor space seamless integration to achieve a full representation of both interior and exterior buildings is also heavily in demand.

show abstract

Double Refinement Network for Room Layout Estimation

Cited by 4 publications

References 20 publications

Heightfields for Efficient Scene Reconstruction for AR

Heightfields for Efficient Scene Reconstruction for AR

Semantic Room Wireframe Detection from a Single View

A Review of Techniques for 3D Reconstruction of Indoor Environments

Contact Info

Product

Resources

About