PhD Candidate | EPFL

Chenghao Xu

“Anything one man can imagine, other men can make real.” - Jules Verne

I am currently pursuing my Ph.D. supervised by Prof. Olga Fink at École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, and closely collaborating with Schindler. Before this, I completed my M.Sc. in Robotics at the Delft University of Technology (TU Delft), Netherlands, and a B.Eng. in Mechanical Engineering with distinction from the Southern University of Science and Technology, China.

During my master's studies, I worked on robust dynamic visual SLAM systems and realistic dynamic environment simulations with Prof. Aamir Ahmad at the Max Planck Institute for Intelligent Systems, Tübingen, Germany.

Inspired by the fantasies of Jules Verne and Isaac Asimov, I am captivated by the elegance of intelligent systems, which propels me to explore the intersections between the physical world and artificial intelligence. My current research interests lie in 3D vision and scene reconstruction, particularly in multimodal reconstruction for building assessment and renovation.

News

Feb 26, 2025 ChatGarment 🧣 is accepted to CVPR 2025.
Feb 13, 2025 BuildNet3D 🏗️ got accepted by Building and Environment Journal.
Dec 06, 2024 Excited to present BuildNet3D at FoC 2024 and AMLD 2025.
Aug 08, 2024 My first paper DynaPix SLAM is accepted to DAGM GCPR 2024.
Jun 24, 2024 Our research on upper-limb exoskeleton has been accepted by TMECH.
Apr 20, 2024 I'm thrilled to attend the ETH Robotics Summer School this summer!
May 07, 2023 Our work got accepted to ICRA 2023 Workshop on Active Methods in Autonomous Navigation.
May 06, 2023 Our work got accepted to ICRA 2023 Workshop on Pretraining for Robotics.
Dec 31, 2022 GRADE was accepted for presentation at NVIDIA GTC 2023.
Jun 30, 2022 I will work as a research assistant at MPI-IS this summer.
Feb 10, 2022 I will work on novel and impactful solutions with Spot robots in YES! Delft Impact Lab 🐕
Feb 01, 2022 I am currently working as a Computer Vision R&D Engineer at Lely Technologies 🐄
Jul 01, 2021 First time in Beijing: I will work as a control engineer at ROKAE Robotics.
Aug 25, 2020 Admission to Master Robotics at Delft University of Technology 🏰
Jun 30, 2020 I graduated from Southern University of Science and Technology with Excellent Graduate Honor!

Selected Publications

Paper

Loc²: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching

Z. Xia*, C. Xu*, and A. Alahi

International Conference on Learning Representations (ICLR), 2026

ARXIV

Paper

GRADE: Generating Realistic and Dynamic Environments for Robotics Research with Isaac Sim

E. Bonetto, C. Xu, and A. Ahmad

International Journal of Robotics Research (IJRR), 2025

ARXIV CODE WEBSITE

Paper

Exploiting Semantic Scene Reconstruction for Estimating Building Envelope Characteristics

C. Xu, M. Mielle, A. Laborde, A. Waseem, F. Forest, and O. Fink

Building and Environment, 2025

ARXIV WEBSITE

Paper

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

S. Bian, C. Xu, Y. Xiu, A. Grigorev, Z. Liu, C. Lu, M. J. Black, and Y. Feng

Computer Vision and Pattern Recognition Conference (CVPR), 2025

ARXIV WEBSITE

Paper

DynaPix SLAM: A Pixel-Based Dynamic Visual SLAM Approach

C. Xu*, E. Bonetto*, and A. Ahmad

DAGM German Conference on Pattern Recognition (GCPR), 2024

ARXIV CODE WEBSITE

Paper

Implementation of a Long-Lasting, Untethered, Lightweight, Upper Limb Exoskeleton

H. Liu, K. Fang, L. Chen, C. Xu, C. Chen, T. Wang, Z. Wu, J. Ye, C. Fu, G. Chen, and H. Wang

IEEE/ASME Transactions on Mechatronics (TMECH), 2024

DOI HTML

Talk

Breaking the Wall of Intensive Work Above Head: Design of Passive Upper-Limb Exoskeleton

C. Xu

Falling Walls Lab, November 2019

VIDEO

Featured Projects

Generating Realistic Animated Dynamic Environments

CODE WEBSITE SLAM Dataset

With GRADE framework we generate photorealistic indoor environment datasets consisting of static/dynamic scenarios and extended assets (motion blur, sensor noise, etc.). Generated data has been extensively tested on various SLAM frameworks and typical detection/segmentation libraries to prove usability and improved performance.

Lightweight Adaptive Upper-Limb Exoskeleton

VIDEO Robot Design Exoskeleton

The passive adjustable arm-exoskeleton is designed based on a spring slider model and four-bar-linkage model. It is a lightweight wearable system with a weight of 2 kg and with a feature of easy adjustability.

Multi-Camera Real-Time Surveillance VIDEO Stitching

CODE Computer Vision Image Stitching In Progress

Based on the AutoStitch framework, the feature matching strategy is developed given the corresponding ROIs since the cameras for surveillance are of constant parameters. Furthermore, seam-based optimization will be implemented to improve the stitching performance of the overlapping area.

Online Trajectory Planning for Manipulators Based on Discrete-Time Double-S Profile

CODE Online Planning

Implemented real-time path following movement based on the PID method and double S profile. The constraint-based PID method can achieve synchronous movement for all joints within dynamics constraints.

TIAGo Robot for Expiring Items Picking in Retail Environment

VIDEO Course YOLOv5 Behavior Tree

Constructed ROS behavior tree architecture to dynamically adjusts goals and performs items picking/placing in sequence.

Machine Learning for Car Racing Games

Course Machine Learning

Developed the Random Forest and Convolutional Neural Network models for multi-class classification, which used the current top-view image as input and outputted the control action (accelerate, steer left/right, brake).

Obstacle Detection and Avoidance for Autonomous Vehicle

Course ROS C++

Developed software on ROS to achieve autonomous driving in a simulated test track. Designed ROS nodes to detect obstacles and pedestrians from LiDAR pointclouds and camera images using PCL and OpenCV, and use these detections to generate simple control instructions.

Path Planner for Quadrotor Based on Kinodynamics RRT* and k-PRM Methods

PDF CODE Planning In Progress

Developed RRT* and k-PRM path planner to generate collision-free path to verify the robustness on 3D random obstacle map. Furthermore, vehicle routing problem will be implemented to achieve path planning for multi-rbots with multiple goals.