Skip to yearly menu bar Skip to main content


Poster

Estimating Generic 3D Room Structures from 2D Annotations

Denys Rozumnyi · Stefan Popov · Kevis-kokitsi Maninis · Matthias Niessner · Vittorio Ferrari

Great Hall & Hall B1+B2 (level 1) #306

Abstract:

Indoor rooms are among the most common use cases in 3D scene understanding. Current state-of-the-art methods for this task are driven by large annotated datasets. Room layouts are especially important, consisting of structural elements in 3D, such as wall, floor, and ceiling. However, they are difficult to annotate, especially on pure RGB video. We propose a novel method to produce generic 3D room layouts just from 2D segmentation masks, which are easy to annotate for humans. Based on these 2D annotations, we automatically reconstruct 3D plane equations for the structural elements and their spatial extent in the scene, and connect adjacent elements at the appropriate contact edges. We annotate and publicly release 2246 3D room layouts on the RealEstate10k dataset, containing YouTube videos. We demonstrate the high quality of these 3D layouts annotations with extensive experiments.

Chat is not available.