Haonan Dong 董皓男
I will be an engineer at XGRIDS in July, where I will continue
my work in 3D computer vision. Before that, I
got my
master degree at
CVRS(Computer Vision & Remote
Sensing Lab), Wuhan University, where
I work on 3D computer vision and I am supervised by Prof.
Jian Yao. In July, 2022, I was fortunately worked with Prof. Lingjie Liu on NeRF.
I am interested in most 3D techs including Neural Radiance Field (NeRF),
Multi-View Stereo(MVS),
Structure
from
Motion (SfM) and Augmented Reality (AR). My dream is to build an automatic machine for measuring all
the 3D data in our daily life.
I also finished my bachelor's degree in Wuhan University. Awards and more information are listed in
my CV.
Email  / 
CV  / 
Github
|
|
Publications
I'm interested in 3D computer vision. Much of my
research is about inferring the physical world (structure, motion, shape, etc) from images by
Neural Radiance Field (NeRF), Structure from Motion (SfM) and
Multi-view Stereo (MVS).
Representative papers are highlighted.
|
|
Learning-Based Encoded Target Detection on Iteratively Orthorectified Images for Accurate Fisheye
Calibration.
Haonan Dong, Jian Yao*, Ye Gong, Li Li,
Shaoshen Cao, Yuxuan Li.
The Photogrammetric Record, 2023
paper
page
We present a circular-pattern calibration board that has
rotational invariance. Experiments prove that this board
with the proposed pipeline is all you need for the comprehensive
optical camera calibration task.
|
|
View-Graph Key-Subset Extraction from Efficient and Robust Structure from Motion.
Ye Gong, Pengwei Zhou, Yuyue Liu, Haonan Dong, Li Li, Jian Yao*
The Photogrammetric Record, 2023
paper
page
An approach for view-graph key-subset extraction is proposed to address the data redundancy and
uneven distribution problem in SfM. Experiments conducted on a variety of datasets demonstrate
the advantages of our approach in efficiency, robustness and even accuracy compared to SOTA
methods.
|
|
PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for
Weakly-Textured Surface Reconstruction. Arxiv Preprint 2022 (
arXiv:2203.02156
)
Haonan Dong, Jian Yao*
We present several robust unsupervised learning loss functions for Multi-View Stereo and
our
method reaches
the performance of the state-of-the-art.
|
|
Emergency Evacuation Path Planning Algorithm for
Indoor Fire in Commercial Buildings (In Chinese).
Haonan Dong,
Xiaotong Ye,
Congpu Hao
Journal of Geomatics, 2021
paper
page
Our algorithm can preferentially evacuate
the rooms near the fire origin,avoid the indoor congestion,and
ensure the stability of the evacuation plan.
|
Projects
I work with my teammates to do some interesting things with 3D technologies.
Representative works are highlighted.
|
|
Instant Neural Implicit Field Surface Reconstruction. (Summer Intern, 2022)
Haonan Dong, Lingjie Liu
By integrating NeuS into the instant-ngp framework, and the performance is 6X
faster
than the official implementation. Currently I work on the density-grid accelerating
by
the ray marching algorithm to further enhance the performance..
|
|
Highly-Precise Point Clouds Reconstruction with RGB-D Camera (Done).
Haonan Dong, Pengwei Zhou,
Jian Yao, Ran Ding (Huawei Inc)
We propose a novel strategy to optimize the depth computed from a RGB-D camera
and
the
low-accuracy poses from a lightweight online VO. After the optimization, the
poses
and
the depth are precise enough to rebuild a high-quality model with a simple RGB-D
hardware, say the iPad Pro with the TOF camera.
|
|
Multi-Camera System Intrinsic and Extrinsic Calibration (Done).
Haonan Dong,
Yuyue Liu,
Fei Sun,
Jian Yao,
Shaosheng Cao(Didi Global),
Yuxuan Li(Didi Global)
Currently, we are designing a cheap calibration solution for the
multi-camera
intrinsic
and
extrinsic calibration, from the pinhole to the fish-eye, from the monocular
to
the
stereo..
|
|
Online 3D Reconstruction System with High-Performance Computing Cluster
(Done).
Haonan Dong, Hongche Yin, Lei Luo, Han Fang, Jian Yao
We present a whole pipeline to get real model (eg. depth maps, textured
meshes,
etc.)
from multi-view images or videos, and other applications including
getting
the
real-scale maps for the AR usage.
|
|
Real Scale Map For AR based on Structure from Motion. (Done).
Haonan Dong,
Hongche Yin,
Lei Luo,
Jian Yao
Using the printed ArUco Marker, we optimize the whole sparse point
cloud by bundle adjustment with the real scale. Experiments show
that
our method can recover the real scale of the map and can be directly
used in the AR applications..
|
Services
Paper Reviewer : IROS 2022, ISPRS
|
Open-Source
RGB
3D Reconstruction
Pipeline : Currently, I developed a software based on
classic
open-src
codes to reconstruct a textured mesh from video or RGB image
sequences.
Depth
Fusion : This software can fuse the depth from multi-view
stereo
result or sensors with known poses with two strategies. One is
to
use
the
view selection strategy of COLMAP, and the other is to merge the
neighboring
two images.
Awesome
Indoor Reconstruction : A curated list of awesome indoor
reconstruction methods and datasets.
|
|