Hengyi Wang

Hengyi Wang | 王恒一

I am a PhD student (Jan. 2023 - 2027), working with Prof. Lourdes Agapito at CDT in Foundational AI at University College London. My research topic is Neural Surface Reconstruction from Video.

I obtained my Master degree with thesis on "Neural Representations for 3D Reconstruction" at UCL, suprvised by Prof. Lourdes Agapito. Prior to UCL, I obtained a bachelor degree at joint degree programme between QMUL and BUPT, worked with Prof. Changejae Oh.

Feel free to drop me a message if you would like to know more about my research or just up for a casual chat :)

Email / CV / Google Scholar / Linkedin / Github / Notebooks /

Research

I'm interested in computer vision, deep learning, and generative models. My current research focuses on 3D reconstruction from images. I'm especially passionate about the challenge of perceiving and simultaneously 'dreaming up' the physical world from images.

	3D Reconstruction with Spatial Memory Hengyi Wang, Lourdes Agapito 3DV, 2025 project page / arXiv / code / video We present Spann3R, a transformer-based model that achieves incremental reconstruction from uncalibrated image collection with a simple forward pass.
	MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video Hengyi Wang, Jingwen Wang, Lourdes Agapito CVPR, 2024 project page / arXiv / code / video We present MorpheuS, a dynamic scene reconstruction method that leverages neural implicit representations and diffusion priors for achieving 360° reconstruction of a moving object from a monocular RGB-D video.
	Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM Hengyi Wang, Jingwen Wang, Lourdes Agapito CVPR, 2023 project page / arXiv / code / video We present a neural RGB-D SLAM system, Co-SLAM, which performs robust camera tracking and high-fidelity surface reconstruction in real time. This paper extends the work presented in my MSc thesis.
	Boosting Video Object Segmentation Based on Scale Inconsistency Hengyi Wang, Changjae Oh ICME, 2022 project page / arXiv / code / video We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models based on scale inconsistency. Our work consists of a multi-scale attention module with the corresponding self-supervised online adaptation strategy.
	Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings Hengyi Wang, Chaoran Zhu, Ziyin Ma, Changjae Oh ICASSP Grand Challenge: Rank 1^st, 2022 challenge page / arXiv / code We present a framework to estimate phyiscal properties of the house-hold containers and its fillings from RGB-D and audio inputs. Rank 1^st in the CORSMAL Challenge 2022.

Thesis
	Neural Representations for 3D Reconstruction Master thesis at UCL, 2022 paper / code Built a neural RGB-D surface reconstruction system based on joint coordinate and sparse parametric encoding.

Notes
	Reading: CS236 Deep Generative Models Stefano Ermon, Yang Song, notes

Academic Services

Conference Reviewer: IROS
Journal Reviewer: RA-L
Teaching assistant: Machine Vision, Image Processing

Thanks Jon Barron for the website.