Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
Ranked #1 on 3D Object Classification on 3R-Scan
Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning.
We propose a framework that ameliorates this issue by performing scene reconstruction and semantic scene completion jointly in an incremental and real-time manner, based on an input sequence of depth maps.
There is a high demand of 3D data for 360Â° panoramic images and videos, pushed by the growing availability on the market of specialized hardware for both capturing (e. g., omnidirectional cameras) as well as visualizing in 3D (e. g., head mounted displays) panoramic images and videos.
Ranked #12 on Semantic Segmentation on Stanford2D3D Panoramic
While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects.
We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time.
Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction.