Geometry Enhancements from Visual Content: Going Beyond Ground Truth

12/15/2020
by   Liran Azaria, et al.
0

This work presents a new cyclic architecture that extracts high-frequency patterns from images and re-insert them as geometric features. This procedure allows us to enhance the resolution of low-cost depth sensors capturing fine details on the one hand and being loyal to the scanned ground truth on the other. We present state-of-the-art results for depth super-resolution tasks and as well as visually attractive, enhanced generated 3D models.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 8

page 11

research
11/08/2021

S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Process

We present a super-resolution model for an advection-diffusion process w...
research
09/14/2020

AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results

This paper reviews the video extreme super-resolution challenge associat...
research
03/16/2023

Depth Super-Resolution from Explicit and Implicit High-Frequency Features

We propose a novel multi-stage depth super-resolution network, which pro...
research
07/27/2016

ATGV-Net: Accurate Depth Super-Resolution

In this work we present a novel approach for single depth map super-reso...
research
10/20/2020

SoccerMap: A Deep Learning Architecture for Visually-Interpretable Analysis in Soccer

We present a fully convolutional neural network architecture that is cap...
research
06/02/2020

Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution

Despite the remarkable progresses made in deep-learning based depth map ...
research
01/11/2020

Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN

Low quality depth poses a considerable challenge to computer vision algo...

Please sign up or login with your details

Forgot password? Click here to reset