Explanipedia

Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline Open

Zhihao Zhang, Chunyu Lin, Lang Nie, Jiyuan Wang, Yao Zhao · 2025

As automatic parking systems evolve, the accurate detection of parking slots has become increasingly critical. This study focuses on parking slot detection using surround-view cameras, which offer a comprehensive bird's-eye view of the par…

Robust Image Stitching with Optimal Plane Open

Lang Nie, Mei Yuan, Kang Liao, Yunqiu Xu, Chunyu Lin , et al. · 2025

We present \textit{RopStitch}, an unsupervised deep image stitching framework with both robustness and naturalness. To ensure the robustness of \textit{RopStitch}, we propose to incorporate the universal prior of content perception into th…

TransVFC: A transformable video feature compression framework for machines Open

Yuxiao Sun, Yao Zhao, Meiqin Liu, Chao Yao, Huihui Bai , et al. · 2025

StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps Open

Lang Nie, Chunyu Lin, Kang Liao, Yun Zhang, Yao Zhao · 2025

We retarget video stitching to an emerging issue, named warping shake, which unveils the temporal content shakes induced by sequentially unsmooth warps when extending image stitching to video stitching. Even if the input videos are stable,…

You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splatting Open

Zhijie Shen, Chunyu Lin, Shen-Ming Huang, Lang Nie, Kang Liao , et al. · 2025

Recently, reconstructing scenes from a single panoramic image using advanced 3D Gaussian Splatting (3DGS) techniques has attracted growing interest. Panoramic images offer a 360$\times$ 180 field of view (FoV), capturing the entire scene i…

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation Open

Jiyuan Wang, Chunyu Lin, Cheng Guan, Lang Nie, Jing He , et al. · 2025

In this paper, we propose Jasmine, the first Stable Diffusion (SD)-based self-supervised framework for monocular depth estimation, which effectively harnesses SD's visual priors to enhance the sharpness and generalization of unsupervised p…

Defect Detection in Freight Trains Using a Lightweight and Effective Multi-Scale Fusion Framework with Knowledge Distillation Open

Zhanchang Ma, Shijie Zhou, Chunyu Lin · 2025

The safe operation of freight train equipment is crucial to the stability of the transportation system. With the advancement of intelligent monitoring technology, vision-based anomaly detection methods have gradually become an essential ap…

FishFormer: Annulus Slicing-based Transformer for Fisheye Rectification Open

Shangrong Yang, Chunyu Lin, Kang Liao, Yao Zhao · 2025

Numerous significant progress on fisheye image rectification has been achieved through CNN. Nevertheless, constrained by a fixed receptive field, the global distribution and the local symmetry of the distortion have not been fully exploite…

What Really Matters for Learning-based LiDAR-Camera Calibration Open

Shujuan Huang, Chunyu Lin, Yao Zhao · 2025

Calibration is an essential prerequisite for the accurate data fusion of LiDAR and camera sensors. Traditional calibration techniques often require specific targets or suitable scenes to obtain reliable 2D-3D correspondences. To tackle the…

Revisiting Monocular 3D Object Detection with Depth Thickness Field Open

Qiude Zhang, Chunyu Lin, Zhijie Shen, Niklaus P. Lang, Yao Zhao · 2024

Monocular 3D object detection is challenging due to the lack of accurate depth. However, existing depth-assisted solutions still exhibit inferior performance, whose reason is universally acknowledged as the unsatisfactory accuracy of monoc…

CurrI2P: Inter- and Intra-Modality Similarity Curriculum Learning for Image-to-Point Cloud Registration Open

Liwei Lin, Chunyu Lin, Lang Nie, Shujuan Huang, Yao Zhao · 2024

Image-to-point cloud (I2P) registration aims to align 2D images and 3D point clouds within the same scene. However, existing methods neglect the differences in learning difficulties among different samples, failing to bridge the image-to-p…

Toward Oriented Fisheye Object Detection: Dataset and Baseline Open

Jialin Yang, Chunyu Lin, Lang Nie, Zisen Kong, Jiapeng Wang , et al. · 2024

Fisheye object detection is challenging due to the fisheye distortion, which inclines objects to different extents and pushes extensive irrelevant pixels into the predicted horizontal bounding box (HBB). To address the problems above, we e…

Digging into Contrastive Learning for Robust Depth Estimation with Diffusion Models Open

Jiyuan Wang, Chunyu Lin, Lang Nie, Kang Liao, Shuwei Shao , et al. · 2024

Recently, diffusion-based depth estimation methods have drawn widespread\nattention due to their elegant denoising patterns and promising performance.\nHowever, they are typically unreliable under adverse conditions prevalent in\nreal-worl…

Remaining Useful Life Prediction of Rolling Bearings Based on Time-Frequency Enhanced Transformer Model Open

Chunyu Lin, Hongli Luo, Zhenpeng Wu, Liangwei Zhang · 2024

Deep learning has achieved a lot of progress in predicting Remaining Useful Life (RUL). However, contemporary deep learning frameworks face inherent limitations, including constrained receptive fields, difficulties in capturing long-term d…

Validating Large-Scale Quantum Machine Learning: Efficient Simulation of Quantum Support Vector Machines Using Tensor Networks Open

Kuan‐Cheng Chen, Tai-Yue Li, Yun-Yuan Wang, Simon See, Chun‐Chieh Wang , et al. · 2024

We present an efficient tensor-network-based approach for simulating large-scale quantum circuits, demonstrated using Quantum Support Vector Machines (QSVMs). Our method effectively reduces exponential runtime growth to near-quadratic scal…

Eliminating Warping Shakes for Unsupervised Online Video Stitching Open

Lang Nie, Chunyu Lin, Kang Liao, Yun Zhang, Shuaicheng Liu , et al. · 2024

In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warped content in non-overlapping regions, despite image stitch…

Deep-computer-generated holography with temporal-focusing and a digital propagation matrix for rapid 3D multiphoton stimulation Open

Liang-Wei Chen, Shang-Yang Lu, Feng‐Chun Hsu, Chunyu Lin, Ann‐Shyn Chiang , et al. · 2024

Deep learning-based computer-generated holography (DeepCGH) has the ability to generate three-dimensional multiphoton stimulation nearly 1,000 times faster than conventional CGH approaches such as the Gerchberg-Saxton (GS) iterative algori…

Adapsyn: Anomaly Detection Based on Triplet Training with Adaptive Anomaly Synthesis (Chinamm2024) Open

Shijie Zhou, Chunyu Lin, Zisong Chen, Baoqing Guo, Yao Zhao · 2024

Clinical Outcomes of Laser Hemorrhoidoplasty with Feeding Vessels Suture Ligation. A Retrospective Study in a Single Center Open

Kai‐Hsiang Chen, Yi-Ling Huang, Chunyu Lin, Ming-Cheng Chen, Teng-Yi Chiu , et al. · 2023

Background Laser hemorrhoidoplasty has demonstrated significant therapeutic effectiveness. In order to diminish postoperative bleeding and enhance overall outcomes, we have additionally adopted suture-ligating the feeding vessels. This stu…

WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions Open

Jiyuan Wang, Chunyu Lin, Lang Nie, Shujun Huang, Yao Zhao , et al. · 2023

Depth estimation models have shown promising performance on clear scenes but fail to generalize to adverse weather conditions due to illumination variations, weather particles, etc. In this paper, we propose WeatherDepth, a self-supervised…

Developing a Robotic Surgical Platform Is Beneficial to the Implementation of the ERAS Program for Colorectal Surgery: An Outcome and Learning Curve Analysis Open

Chun-Yen Hung, Chunyu Lin, Ming‐Cheng Chen, Teng-Yi Chiu, Tzu-Wei Chiang , et al. · 2023

Background: Robotic surgery and ERAS protocol care are both prominent developments and have each become global trends. However, the effects and learning curves of combining robotic surgery and ERAS care in colorectal resection have not yet…

Freeform Graphene Oxide-Quantum Dot Microstructures via Multiphoton Crosslinking Open

Chunyu Lin, Shean‐Jen Chen · 2023

Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real Generalization Open

Shangrong Yang, Chunyu Lin, Kang Liao, Yao Zhao · 2023

Fisheye image rectification has a long-term unresolved issue with synthetic-to-real generalization. In most previous works, the model trained on the synthetic images obtains unsatisfactory performance on the real-world fisheye image. To th…

Dual-resonant scanning multiphoton microscope with ultrasound lens and resonant mirror for rapid volumetric imaging Open

Chia-Wei Hsu, Chunyu Lin, Yvonne Yuling Hu, Shean‐Jen Chen · 2023

Learning curve and surgical outcome of robotic assisted colorectal surgery with ERAS program Open

Chunyu Lin, Yi‐Chun Liu, Ming‐Cheng Chen, Feng‐Fan Chiang · 2022

One-step metallization of weft-knitted fabrics for wearable biaxial strain sensors Open

Chao-Yi Tai, Chunyu Lin, Tang-Chun Liu, Lu-Chiang Jia, Thomas Jones , et al. · 2022

Light-field microscopy with temporal focusing multiphoton illumination for scanless volumetric bioimaging Open

Feng‐Chun Hsu, Chunyu Lin, Yvonne Yuling Hu, Y. Hwu, Ann‐Shyn Chiang , et al. · 2022

A temporal focusing multiphoton illumination (TFMI) method is proposed for achieving selective volume illumination (SVI) (i.e., illuminating only the volume of interest) in light-field microscopy (LFM). The proposed method minimizes the ba…

Dual-resonant scanning multiphoton microscope with ultrasound lens and resonant mirror for rapid volumetric imaging Open

Chia-Wei Hsu, Chunyu Lin, Yvonne Yuling Hu, Shean‐Jen Chen · 2022

A dual-resonant scanning multiphoton (DRSM) microscope incorporating a tunable acoustic gradient index of refraction lens and a resonant mirror is developed for high-speed volumetric imaging. In the proposed microscope, the pulse train sig…

Three-dimensional-generator U-net for dual-resonant scanning multiphoton microscopy image inpainting and denoising Open

Chia‐Wei Hsu, Chunyu Lin, Yvonne Yuling Hu, Chi-Yu Wang, Shin‐Tsu Chang , et al. · 2022

A dual-resonant scanning multiphoton (DRSM) microscope incorporating a tunable acoustic gradient index of refraction lens and a resonant mirror is developed for rapid volumetric bioimaging. It is shown that the microscope achieves a volume…

Temporal Consistency Learning of Inter-Frames for Video Super-Resolution Open

Meiqin Liu, Shuo Jin, Chao Yao, Chunyu Lin, Yao Zhao · 2022

Video super-resolution (VSR) is a task that aims to reconstruct\nhigh-resolution (HR) frames from the low-resolution (LR) reference frame and\nmultiple neighboring frames. The vital operation is to utilize the relative\nmisaligned frames f…

Chunyu Lin YOU? Author Swipe