activity
20172021
most citedConvolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling

2 citations · 2 across the 4 of their papers we have counts for

collaborators

10 papers

math.MG2021

Hausdorff Dimension and Lebesgue Measure of Codiagonal of Embedded Vector Bundles over Submanifolds in Euclidean Space

Hanwen Liu

In this paper we study measure theoretical size of the image of naturally embedded vector bundles in under the codiagonal morphism, i.e. $Δ_{…

eess.IV2021

Back-Projection Pipeline

Pablo Navarrete Michelini, Hanwen Liu, Yunhua Lu +1

We propose a simple extension of residual networks that works simultaneously in multiple resolutions. Our network design is inspired by the iterative back-projection algorithm but…

eess.IV2021

Multi-Grid Back-Projection Networks

Pablo Navarrete Michelini, Wenbin Chen, Hanwen Liu +2

Multi-Grid Back-Projection (MGBP) is a fully-convolutional network architecture that can learn to restore images and videos with upscaling artifacts. Using the same strategy of mul…

cs.CV2020

Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences

Guangming Wang, Muyao Chen, Hanwen Liu +3

With the rapid development of measurement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perce…

eess.IV2019

MGBPv2: Scaling Up Multi-Grid Back-Projection Networks

Pablo Navarrete Michelini, Wenbin Chen, Hanwen Liu +1

Here, we describe our solution for the AIM-2019 Extreme Super-Resolution Challenge, where we won the 1st place in terms of perceptual quality (MOS) similar to the ground truth and…

cs.CV2019

A Tour of Convolutional Networks Guided by Linear Interpreters

Pablo Navarrete Michelini, Hanwen Liu, Yunhua Lu +1

Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the in…