Search Results for author:
Found 45 papers, 8 papers with code
PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth
In this paper, we introduce PosePilot, a lightweight yet powerful framework that significantly enhances camera pose controllability in generative world models.
Adaptive Detection of Fast Moving Celestial Objects Using a Mixture of Experts and Physical-Inspired Neural Network
However, the growing prevalence of space-based telescopes, along with their diverse observational modes, produces images with different properties, rendering conventional methods less effective.
TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference
Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity.
VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detection
Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data.
StyledStreets: Multi-style Street Simulator with Spatial and Temporal Consistency
Urban scene reconstruction requires modeling both static infrastructure and dynamic elements while supporting diverse environmental conditions.
Finetuning Generative Trajectory Model with Reinforcement Learning from Human Feedback
To address this, we introduce TrajHF, a human feedback-driven finetuning framework for generative trajectory models, designed to align motion planning with diverse driving preferences.
Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latant Space
In addition, it remains a challenge to match multiple trajectories with each vehicle in the video to control the video generation.
UniPLV: Towards Label-Efficient Open-World 3D Scene Understanding by Regional Visual Language Supervision
We present UniPLV, a powerful framework that unifies point clouds, images and text in a single learning paradigm for open-world 3D scene understanding.
GaussianAD: Gaussian-Centric End-to-End Autonomous Driving
We initialize the scene with uniform 3D Gaussians and use surrounding-view images to progressively refine them to obtain the 3D Gaussian scene representation.
ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
This is complemented by a progressive data update strategy designed to ensure high-quality rendering for more complex maneuvers.
Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
These planners promise better generalizations on complicated and few-shot cases than previous methods.
DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation
Engagement estimation plays a crucial role in understanding human social behaviors, attracting increasing research interests in fields such as affective computing and human-computer interaction.
DiVE: DiT-based Video Generation with Enhanced Control
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e. g. problematic maneuvers in corner cases.
RMFA-Net: A Neural ISP for Real RAW to RGB Image Reconstruction
It is demonstrated that RMFA-Net outperforms previous algorithms, achieving a PSNR score of over 25 dB, surpassing the state-of-the-art by +1 dB.
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking
In this paper, we first summarize the current end-to-end 3D MOT framework by decomposing it into three constituent parts: query initialization, query propagation, and query matching.
Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation
Instead of randomly generating new data, we further design a sampling policy to let Delphi generate new data that are similar to those failure cases to improve the sample efficiency.
A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model
Hence, as an example to present how to overcome the issue, we built a framework for general analysis of galaxy images, based on a large vision model (LVM) plus downstream tasks (DST), including galaxy morphological classification, image restoration, object detection, parameter extraction, and more.
An Image Quality Evaluation and Masking Algorithm Based On Pre-trained Deep Neural Networks
With the growing amount of astronomical data, there is an increasing need for automated data processing pipelines, which can extract scientific information from observation data without human interventions.
Motion planning for off-road autonomous driving based on human-like cognition and weight adaptation
Then, based on human-like generated trajectories in different environments, we design a primitive-based trajectory planner that aims to mimic human trajectories and cost weight selection, generating trajectories that are consistent with the dynamics of off-road vehicles.
CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes.
A Data-Driven Approach for Mitigating Dark Current Noise and Bad Pixels in Complementary Metal Oxide Semiconductor Cameras for Space-based Telescopes
In this paper, we introduce a data-driven framework for mitigating dark current noise and bad pixels for CMOS cameras.
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors.
PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments
With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes.
BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving
Furthermore, there lack of well-formed retrieval datasets for effective evaluation.
Guidelines in Wastewater-based Epidemiology of SARS-CoV-2 with Diagnosis
With the global spread and increasing transmission rate of SARS-CoV-2, more and more laboratories and researchers are turning their attention to wastewater-based epidemiology (WBE), hoping it can become an effective tool for large-scale testing and provide more ac-curate predictions of the number of infected individuals.
Perception of Misalignment States for Sky Survey Telescopes with the Digital Twin and the Deep Neural Networks
To address this, we need a method to obtain misalignment states, aiding in the reconstruction of accurate point spread functions for data processing methods or facilitating adjustments of optical components for improved image quality.
Image Restoration with Point Spread Function Regularization and Active Learning
Large-scale astronomical surveys can capture numerous images of celestial objects, including galaxies and nebulae.
PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments
Reconstructing large-scale 3D scenes is essential for autonomous vehicles, especially when partial sensor data is lost.
Target Detection Framework for Lobster Eye X-Ray Telescopes with Machine Learning Algorithms
Then an algorithm based on morphological operations and two neural networks would be used to detect candidates of celestial objects with different flux from these 2D images.
Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers
We embed prior information of strongly lensed arcs at cluster-scale into the training data through simulation and then train the detection algorithm with simulated images.
Reinforcement Learning for Few-Shot Text Generation Adaptation
Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention.
PNet -- A Deep Learning Based Photometry and Astrometry Bayesian Framework
Time domain astronomy has emerged as a vibrant research field in recent years, focusing on celestial objects that exhibit variable magnitudes or positions.
Smart obervation method with wide field small aperture telescopes for real time transient detection
The ARGUS uses a deep learning based astronomical detection algorithm implemented in embedded devices in each WFSATs to detect astronomical targets.
Point Spread Function Estimation for Wide Field Small Aperture Telescopes with Deep Neural Networks and Calibration Data
Then we use these data to train a DNN (Tel--Net).
Compressive Shack-Hartmann Wavefront Sensor based on Deep Neural Networks
However if there exists strong atmospheric turbulence or the brightness of guide stars is low, the accuracy of wavefront measurements will be affected.
Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
In recent years, developments of deep neural networks and increments of the number of astronomical images have evoked a lot of data--driven image restoration methods.
PSF--NET: A Non-parametric Point Spread Function Model for Ground Based Optical Telescopes
Assuming point spread functions induced by the atmospheric turbulence with the same profile belong to the same manifold space, we propose a non-parametric point spread function -- PSF-NET.
Detection and Classification of Astronomical Targets with Deep Neural Networks in Wide Field Small Aperture Telescopes
To increase the generalization ability of our framework, we use both simulated and real observation images to train the neural network.
Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder
For wide field small aperture telescopes, the point spread function is hard to model, because it is affected by many different effects and has strong temporal and spatial variations.
A systematic review of fuzzing based on machine learning techniques
Next, this paper assesses the performance of the machine learning models based on the frequently used evaluation metrics.
Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
Texture is one of the most obvious characteristics in solar images and it is normally described by texture features.
Perception Evaluation -- A new solar image quality metric based on the multi-fractal property of texture features
Next-generation ground-based solar observations require good image quality metrics for post-facto processing techniques.
Optical Transient Object Classification in Wide Field Small Aperture Telescopes with Neural Networks
In this paper, we propose two transient classification methods based on neural networks.
