Shuaifeng Zhi

I am a PhD student at The Dyson Robotics Lab at Imperial College, supervised by Prof. Andrew J. Davison and Dr. Stefan Leutenegger. My research interest lies in semantic SLAM, combining semantics and SLAM systems using learning-based approaches. Before coming to UK I finished my BSc and MSc of Electrical Engineering in China.

Email  /  Google Scholar  /  LinkedIn  /  Twitter

Event and News

Feb 2019: One paper got accepted to CVPR 2019.

July 2018: Participated International Computer Vision Summer School (ICVSS 2018) in Sicily, Italy.

Publications
PontTuset

Bootstrapping Semantic Segmentation with Regional Contrast
Shikun Liu, Shuaifeng Zhi, Edward Johns, Andrew J. Davison
arxiv pre-print
arxiv / code / project page

We present ReCo, a new contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs (semi-)supervised pixel-level contrastive learning on a sparse set of hard negative pixels. With minimal extra memory footprint, Reco boosts exsiting baselines by a large margin, revealing hierarchical similarities of various semantic classes as well.

PontTuset

In-Place Scene Labelling and Understanding with Implicit Scene Representation
Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger, Andrew J. Davison
arxiv pre-print
arxiv / video / video (bilibili) / project page

We show that neural radiance fileds (NeRF) contains strong priors for scene cluster and segmentation. The internal multi-view consistency and smoothness make the training process itself a multi-view semantic fusion process. Such a scene-specific implcit semantic representation can be efficiently learned with various sparse or noisy annotations, leading to accurate dense labelling of the full scene.

SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger, Andrew J. Davison
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
arxiv / video

We show that an efficient code representation is able to control the semantic label prediction of an image. Latent codes of overlapping images can be jointly optimised to perform coherent semantic fusion. We also show how this approach can be used within a monocular keyframe based semantic mapping system where a similar code approach is used for geometry.

PontTuset

Toward real-time 3D object recognition: A lightweight volumetric CNN framework using multitask learning
Shuaifeng Zhi, Yongxiang Liu, Xiang Li, Yulan Guo
Computers & Graphics, 2017
bibtex

We propose LightNet, a light-weight 3D volumetric CNN for real-time 3D object classification.

This paper subsumes the 3DOR 2017 paper LightNet.

PontTuset

LightNet: A Lightweight 3D Convolutional Neural Network for Real-Time 3D Object Recognition
Shuaifeng Zhi, Yongxiang Liu, Xiang Li, Yulan Guo
Eurographics Workshop on 3D Object Retrieval (3DOR), 2017
bibtex

Service

Reviewer in 2021, CVPR, ICCV, NeurIPS, ICME, IJCNN

Reviewer in 2020, ICME

Reviewer in 2019, CVPR-W, ICCV-W, ICRA-W

Lab Assistant, Robotics (Online with Coppeliasim!), Spring 2021

Lab Assistant, Robotics , Autumn 2019

Lab Assistant, Robotics , Spring 2019

Lab Assistant, Robotics , Autumn 2018

Lab Assistant, Advanced-Robotics, Spring 2018


Thank Dr. Jon Barron for sharing the source code of the website.