Minglin Chen

Minglin Chen

Auto-generated profile, based on publicly available information

Minglin Chen

School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2023 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Open access
ZWZi Wang
Zi Wang
MCMinglin Chen
Minglin Chen
YGYulan Guo
Yulan Guo
ZLZhang Li
Zhang Li
QYQifeng Yu
Qifeng Yu
Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models. To this end, we propose a self-training framework based on the domain-agnostic geometrical constraints . Specifically, we train a neural network to predict the 2D keypoints of a satellite and then use PnP to estimate the pose. The poses of target samples are regarded as latent variables to formulate the task as a minimization problem. Furthermore, we leverage fine-grained segmentation to tackle the information loss issue caused by abstracting the satellite as sparse keypoints. Finally, we iteratively solve the minimization problem in two steps: pseudo-label generation and network training. Experimental results show that our method adapts well to the target domain. Moreover, our method won the 1st place on the sunlamp task of the second international Satellite Pose Estimation Competition.

10 June 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MCMinglin Chen
Minglin Chen
LWLongguang Wang
Longguang Wang
YLYinjie Lei
Yinjie Lei
ZDZilong Dong
Zilong Dong
YGYulan Guo
Yulan Guo
Novel view synthesis aims at rendering any posed images from sparse observations of the scene. Recently, neural radiance fields (NeRF) have demonstrated their effectiveness in synthesizing novel views of a bounded scene. However, most existing methods cannot be directly extended to 360° unbounded scenes where the camera orientations and scene depths are unconstrained with large variations. In this paper, we present a spherical radiance field (SRF) for efficient novel view synthesis in 360° unbounded scenes. Specifically, we represent a 3D scene as multiple concentric spheres with different radii. In particular, each sphere encodes its corresponding layered scene into implicit representations and is parameterized with an equirectangular projection image. A shallow multi-layer perceptron (MLP) is then used to infer the density and color from these sphere representations for volume rendering. Moreover, an occupancy grid is introduced to cache the density field and guide the ray sampling, which accelerates the training and rendering procedures by reducing the number of samples along the ray. Experiments show that our method can well fit 360° unbounded scenes and produces state-of-the-art results on three benchmark datasets with less than 30 minutes of training time on a 3090 GPU, surpassing Mip-NeRF 360 with a 400× speedup. In addition, our method achieves competitive performance in terms of both accuracy and efficiency on a bounded dataset. Project page: https://minglin-chen.github.io/SphericalRF.

31 October 2024
Verified
Book Chapter
Closed access
PDF file
YWYukun Wang
Yukun Wang
KLKunhong Li
Kunhong Li
MCMinglin Chen
Minglin Chen
LWLongguang Wang
Longguang Wang
SZShunbo Zhou
Shunbo Zhou
YGYulan Guo
Yulan Guo

28 October 2024
Verified
Conference Paper
Open access
YWYi Wang
Yi Wang
NZNingze Zhong
Ningze Zhong
MCMinglin Chen
Minglin Chen
LWLongguang Wang
Longguang Wang
YGYulan Guo
Yulan Guo
With the growth of VR and AR industry, 3D reconstruction has become a more and more important topic in multimedia. Although 3D Gaussian Splatting achieves state-of-the-art in 3D Reconstruction, a large number of Gaussians are needed to fit a 3D scene due to the Gibbs Phenomenon. The pursuit of compressing 3D Gaussian Splatting and reducing memory overhead has long been a focal point. Embarking on this trajectory, our study delves into this domain, aiming to mitigate these challenges. Inspired by the tangram, a Chinese ancient puzzle, we introduce a novel methodology (Tangram-Splatting) that leverages shape priors to optimize 3D scene fitting. Central to our approach is a pioneering technique that diversifies Gaussian function types while preserving algorithmic efficiency. Through exhaustive experimentation, we demonstrate that our method achieves a remarkable average reduction of 62.4% in memory consumption used to store optimized parameters and decreases the training time by at least 10 minutes, with only marginal sacrifices in PSNR performance, typically under 0.3 dB, and our algorithm is even better on some datasets. This reduction in memory burden is of paramount significance for real-world applications, mitigating the substantial memory footprint and transmission burden traditionally associated with such algorithms. Our algorithm underscores the profound potential of Tangram-Splatting in advancing multimedia applications.

27 March 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZFZhiheng Fu
Zhiheng Fu
YGYulan Guo
Yulan Guo
MCMinglin Chen
Minglin Chen
QHQingyong Hu
Qingyong Hu
HLHamid Laga
Hamid Laga
Mohammed BennamounMohammed Bennamoun
Mohammed Bennamoun
Semantic instance completion aims to recover the complete 3D shapes of foreground objects together with their labels from a partial 2.5D scan of a scene. Previous works have relied on full supervision, which requires ground-truth annotations, in the form of bounding boxes and complete 3D objects. This has greatly limited their real-world application because the acquisition of ground-truth data is very costly and time-consuming. To address this bottleneck, we propose a Weakly-Supervised Semantic Instance Completion Network (WSSIC-Net), which learns real-world partial point cloud object completion without requiring the ground truth of complete 3D objects. Instead, WSSIC-Net leverages 3D ground-truth bounding boxes, partial objects of a raw scene, and unpaired synthetic 3D point clouds. More specifically, a 3D detector is used to encode partial point clouds into proposal features, which are then fed into two branches. The first branch uses fully supervised box prediction based on proposal features. The second branch, hereinafter called instance completion, leverages the proposal features as partial object features to achieve weakly-supervised instance completion. A Generative Adversarial Network (GAN) completes the partial features of the 2.5D foreground objects of real-world scenes using only unpaired but semantically-consistent complete synthetic point clouds. In our experiments, we demonstrate that the fully-supervised 3D detection and the weakly-supervised instance completion complement one another. The qualitative and quantitative evaluations on the ScanNet v2 dataset demonstrate that the proposed “weakly-supervised” approach consistently achieves comparable performance to the state-of-the-art “fully supervised” methods.

27 March 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JWJunhui Wan
Junhui Wan
ZFZhiheng Fu
Zhiheng Fu
MCMinglin Chen
Minglin Chen
PZPeng Zhang
Peng Zhang
HWHanyun Wang
Hanyun Wang
YGYulan Guo
Yulan Guo
Semantic instance reconstruction attracts increasing attention in several areas such as mobile mapping, scene reconstruction, and robot navigation. Although many progresses have been made in recent years, the reconstruction performance is highly sensitive to occlusions and noises. To address these issues, we incorporate point cloud completion into a novel semantic instance reconstruction network PMNet, which consists of a 3D object detection module, a point cloud completion module, and a mesh generation module. Based on the candidate instance proposals and their proposal features obtained in the object detection module, a point encoder layer is proposed to learn the local geometric features from the point cloud belonging to the detected instances, and a feature transformation layer is utilized to align the proposal features with the local geometric features. These two types of features are then fused and fed into the point cloud decoder to predict the complete point cloud of each instance. The mesh is finally reconstructed for each instance by the mesh generation module. Quantitative and qualitative experiments conducted on the ScanNetv2 dataset demonstrate that the proposed PMNet achieves the best reconstruction performance on real-world point clouds.