In Depth Bayesian Semantic Scene Completion

10/16/2020
by   David Gillsjö, et al.
10

This work studies Semantic Scene Completion which aims to predict a 3D semantic segmentation of our surroundings, even though some areas are occluded. For this we construct a Bayesian Convolutional Neural Network (BCNN), which is not only able to perform the segmentation, but also predict model uncertainty. This is an important feature not present in standard CNNs. We show on the MNIST dataset that the Bayesian approach performs equal or better to the standard CNN when processing digits unseen in the training phase when looking at accuracy, precision and recall. With the added benefit of having better calibrated scores and the ability to express model uncertainty. We then show results for the Semantic Scene Completion task where a category is introduced at test time on the SUNCG dataset. In this more complex task the Bayesian approach outperforms the standard CNN. Showing better Intersection over Union score and excels in Average Precision and separation scores.

READ FULL TEXT

page 1

page 2

page 4

page 8

page 10

research
04/10/2018

Two Stream 3D Semantic Scene Completion

We propose a new paradigm for advancing 3D semantic scene completion bas...
research
11/09/2015

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding

We present a deep learning framework for probabilistic pixel-wise semant...
research
12/29/2017

ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

We introduce ScanComplete, a novel data-driven approach for taking an in...
research
03/29/2021

Bayesian Deep Basis Fitting for Depth Completion with Uncertainty

In this work we investigate the problem of uncertainty estimation for im...
research
06/29/2021

IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement

3D semantic scene completion and 2D semantic segmentation are two tightl...
research
05/15/2019

3D Semantic Scene Completion from a Single Depth Image using Adversarial Training

We address the task of 3D semantic scene completion, i.e. , given a sing...

Please sign up or login with your details

Forgot password? Click here to reset