DeepAI
Log In Sign Up

PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation

05/06/2019
by   Vitor Guizilini, et al.
0

Densely estimating the depth of a scene from a single image is an ill-posed inverse problem that is seeing exciting progress with self-supervision from strong geometric cues, in particular from training using stereo imagery. In this work, we investigate the more challenging structure-from-motion (SfM) setting, learning purely from monocular videos. We propose PackNet - a novel deep architecture that leverages new 3D packing and unpacking blocks to effectively capture fine details in monocular depth map predictions. Additionally, we propose a novel velocity supervision loss that allows our model to predict metrically accurate depths, thus alleviating the need for test-time ground-truth scaling. We show that our proposed scale-aware architecture achieves state-of-the-art results on the KITTI benchmark, significantly improving upon any approach trained on monocular video, and even achieves competitive performance to stereo-trained methods.

READ FULL TEXT

page 1

page 7

page 8

page 14

05/01/2019

Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation

The field of self-supervised monocular depth estimation has seen huge ad...
04/08/2019

Learning monocular depth estimation infusing traditional stereo knowledge

Depth estimation from a single image represents a fascinating, yet chall...
10/04/2019

Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances

Dense depth estimation from a single image is a key problem in computer ...
03/18/2019

Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

Supervised learning methods to infer (hypothesize) depth of a scene from...
12/01/2017

Learning Depth from Monocular Videos using Direct Methods

The ability to predict depth from a single image - using recent advances...
04/30/2020

Consistent Video Depth Estimation

We present an algorithm for reconstructing dense, geometrically consiste...
05/18/2022

Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving

Although existing monocular depth estimation methods have made great pro...