Search Results for author:
Found 25 papers, 7 papers with code
Learning to See in the Dark with Events
A detail enhancing branch is proposed to reconstruct day light-specific features from the domain-invariant representations in a residual manner, regularized by a ranking loss.
TS-SatMVSNet: Slope Aware Height Estimation for Large-Scale Earth Terrain Multi-view Stereo
3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment. Recently, learning-based multi-view stereo~(MVS) methods have shown promise in this task.
EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene
To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations.
PDCFNet: Enhancing Underwater Images through Pixel Difference Convolution
We propose an underwater image enhancement network, PDCFNet, based on PDC and cross-level feature fusion.
Cloud Deployment of Large-Scale Electromagnetic Transient Simulation -- Discovery and Experiences
Electromagnetic Transient (EMT) simulation starts to play a critical role in modern power system planning and operations due to large penetration of inverter based resources (IBRs).
Respiratory Subtraction for Pulmonary Microwave Ablation Evaluation
The experimental results confirm the effectiveness of the respiratory subtraction method and the proposed quantitative evaluation metric in assessing lung tumor treatment.
Mamba-UIE: Enhancing Underwater Images with Physical Model Constraint
These components are reassembled according to the revised underwater image formation model, and the reconstruction consistency constraint is applied between the reconstructed image and the original image, thereby achieving effective physical constraint on the underwater image enhancement process.
ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Model
Experiments demonstrate the effectiveness of our framework, showcasing its ability to generalize well across multiple tasks even under the scarcity of extensively annotated datasets, offering a scalable solution to automatic segmentation and annotation challenges in the field.
NeRO: Neural Road Surface Reconstruction
Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving.
Semantic Is Enough: Only Semantic Information For NeRF Reconstruction
This research aims to extend the Semantic Neural Radiance Fields (Semantic-NeRF) model by focusing solely on semantic output and removing the RGB output component.
TiC: Exploring Vision Transformer in Convolution
While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks.
ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval
Moreover, our method also achieves the lowest $e_{1}$ and $e_{3}$ on the BlendedMVS dataset and the highest Acc and $F_{1}$-score on the ETH 3D dataset, surpassing all listed methods. Project website: https://github. com/zs670980918/ARAI-MVSNet
Pixel-wise rational model for structured light system
This Letter presents a novel structured light system model that effectively considers local lens distortion by pixel-wise rational functions.
A Unified HDR Imaging Method with Pixel and Patch Level
The proposed HyHDRNet consists of a content alignment subnetwork and a Transformer-based fusion subnetwork.
SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders
In this work, we propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR.
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning
In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.
Self-Supervised Intensity-Event Stereo Matching
Event cameras are novel bio-inspired vision sensors that output pixel-level intensity changes in microsecond accuracy with a high dynamic range and low power consumption.
A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinese
Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct pronunciation for several candidates for a Chinese polyphonic character.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Practical Adoption of Cloud Computing in Power Systems- Drivers, Challenges, Guidance, and Real-world Use Cases
Motivated by The Federal Energy Regulatory Commission's (FERC) recent direction and ever-growing interest in cloud adoption by power utilities, a Task Force was established to assist power system practitioners with secure, reliable and cost-effective adoption of cloud technology to meet various business needs.
Unperturbed inverse kinematics nucleon knockout measurements with a 48 GeV/c carbon beam
Measuring the microscopic structure of such systems is a formidable challenge, often met by particle knockout scattering experiments.
Nuclear Experiment Nuclear Theory
Self-Supervised Learning Aided Class-Incremental Lifelong Learning
Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge.
Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.
Deep learning for smart fish farming: applications, opportunities and challenges
This change can create new opportunities and a series of challenges for information and data processing in smart fish farming.
Hybrid calibration procedure for fringe projection profilometry based on stereo-vision and polynomial fitting
The key to accurate 3D shape measurement in Fringe Projection Profilometry (FPP) is the proper calibration of the measurement system.
