Search Results for author:
Found 39 papers, 20 papers with code
Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis
The Change-Agent integrates a multi-level change interpretation (MCI) model as the eyes and a large language model (LLM) as the brain.
RSMamba: Remote Sensing Image Classification with State Space Model
Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation.
Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method
In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field.
Learning to detect cloud and snow in remote sensing images from noisy labels
This paper is the first to consider the impact of label noise on the detection of clouds and snow in remote sensing images.
DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling
Next, we construct hyper-networks based on deep learning methods to directly learn weather patterns from a large amount of meteorological data.
Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection
Change detection, a prominent research area in remote sensing, is pivotal in observing and analyzing surface transformations.
Ranked #6 on
Change Detection
on LEVIR-CD
Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning
The existing methods for Remote Sensing Image Change Captioning (RSICC) perform well in simple scenes but exhibit poorer performance in complex scenes.
High-Quality 3D Face Reconstruction with Affine Convolutional Networks
In our method, an affine transformation matrix is learned from the affine convolution layer for each spatial location of the feature maps.
MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehicles
As vehicular communication and networking technologies continue to advance, infrastructure-based roadside perception emerges as a pivotal tool for connected automated vehicle (CAV) applications.
Zero-shot Text-driven Physically Interpretable Face Editing
Our method can also be flexibly extended to real-time video face editing.
Zero-Shot Image Harmonization with Generative Model Prior
Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image.
Robust Roadside Perception: an Automated Data Synthesis Pipeline Minimizing Human Annotation
Our approach was rigorously tested at two key intersections in Michigan, USA: the Mcity intersection and the State St./Ellsworth Rd roundabout.
RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model
We also propose several ongoing derivatives for instance segmentation tasks, drawing on recent advancements within the SAM community, and compare their performance with RSPrompter.
Continuous Cross-resolution Remote Sensing Image Change Detection
Toward continuous cross-resolution CD, we propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying resolution differences.
Diffusion Models for Imperceptible and Transferable Adversarial Attack
Many existing adversarial attacks generate $L_p$-norm perturbations on image RGB space.
Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation
In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images.
Dense Pixel-to-Pixel Harmonization via Continuous Image Representation
High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing.
Ranked #8 on
Image Harmonization
on iHarmony4
Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework.
Progressive Scale-aware Network for Remote sensing Image Change Captioning
To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers.
Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space
Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models.
Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors
In this paper, we argue that this limited accuracy is due to the bias of their volume rendering strategies, especially when the viewing direction is close to be tangent to the surface.
Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras.
Remote Sensing Novel View Synthesis with Implicit Multiplane Representations
In this paper, we propose a novel remote sensing view synthesis method by leveraging the recent advances in implicit neural representations.
Building Extraction from Remote Sensing Images with Sparse Token Transformers
Deep learning methods have achieved considerable progress in remote sensing image building extraction.
Building change detection for remote sensing images
Extracting Buildings In Remote Sensing Images
Multi-view 3D Reconstruction with Transformer
Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.
Ranked #5 on
3D Reconstruction
on ShapeNet
Single-Shot Motion Completion with Transformer
Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications.
Ranked #2 on
Motion Synthesis
on LaFAN1
MeInGame: Create a Game Character Face from a Single Portrait
To tackle these problems, we propose 1) a low-cost facial texture acquisition method, 2) a shape transfer algorithm that can transform the shape of a 3DMM mesh to games, and 3) a new pipeline for training 3D game face reconstruction networks.
Multi-View 3D Reconstruction With Transformers
Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.
NeuralMagicEye: Learning to See and Understand the Scene Behind an Autostereogram
This paper studies an interesting question that whether a deep CNN can be trained to recover the depth behind an autostereogram and understand its content.
Stylized Neural Painting
Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering.
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles.
Semi-Supervised Learning for In-Game Expert-Level Music-to-Dance Translation
Previous works of this topic consider music-to-dance as a supervised motion generation problem based on time-series data.
Neutral Face Game Character Auto-Creation via PokerFace-GAN
Besides, the neural network based renderer used in previous methods is also difficult to be extended to multi-view rendering cases.
Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
With the rapid development of Role-Playing Games (RPGs), players are now allowed to edit the facial appearance of their in-game characters with their preferences rather than using default templates.
Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images
Considering the layer separating ambiguity that given a single mixed input, there could be an infinite number of possible solutions, we introduce a "Separation-Critic" - a discriminative network which is trained to identify whether the output layers are well-separated and thus further improves the layer separation.
Generative Adversarial Training for Weakly Supervised Cloud Matting
The detection and removal of cloud in remote sensing images are essential for earth observation applications.
Multi-grained Attention Networks for Single Image Super-Resolution
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
Face-to-Parameter Translation for Game Character Auto-Creation
Character customization system is an important component in Role-Playing Games (RPGs), where players are allowed to edit the facial appearance of their in-game characters with their own preferences rather than using default templates.
Object Detection in 20 Years: A Survey
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.
