Weijian Xie

Entropy-Guided Fusion with GDA Refinement for Few-Shot Remote Sensing Vision-Language Models

Yong Sun, Hongxin Huang, Weijian Xie

cn (code pays fourni par la source)

Collaborative Distillation for Few-Shot Image Classification on Edge Devices

Weijian Xie, Yong Sun, Qianxi Cheng, Fuhai Zhao et autres

cn (code pays fourni par la source)

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu et autres

Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. …

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu et autres

Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. …

Low-data cross-modal adaptation for remote sensing with proxy-enhanced multi-granularity feature caching

Yong Sun, Qianxi Cheng, Weijian Xie, Hongxin Huang et autres

Despite the potential of vision-language models for open-vocabulary recognition, their deployment in remote sensing is limited by the limited effectiveness of generic prompts, the scarcity of annotated datasets, and insufficient domain-specific feature discriminability. To address these limitations, we propose a proxy-enhanced multi-granularity …

cn (code pays fourni par la source)

InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu et autres

We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time …

InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu et autres

We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time …

Zero-shot adapter framework for cross-modal classification of remote sensing imagery

Yong Sun, Weijian Xie, Hongxin Huang, Chengcheng Gu

cn (code pays fourni par la source)

StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation

Shangjin Zhai, Zhichao Ye, Jialin Liu, Weijian Xie et autres

Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging. To address …

cn (code pays fourni par la source)

XR-VIO: High-precision Visual Inertial Odometry with Fast Initialization for XR Applications

Shangjin Zhai, Nan Wang, Xiaomeng Wang, Danpeng Chen et autres

This paper presents a novel approach to Visual Inertial Odometry (VIO), focusing on the initialization and feature matching modules. Existing methods for initialization often suffer from either poor stability in visual Structure from Motion (SfM) or fragility in solving a huge number …

StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation

Shangjin Zhai, Zhichao Ye, Jialin Liu, Weijian Xie et autres

Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging. To address …

PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

Danpeng Chen, Weicai Ye, Yifan Wang, Weijian Xie et autres

Recently, 3D Gaussian Splatting (3DGS) has attracted widespread attention due to its high-quality rendering, and ultra-fast training and rendering speed. However, due to the unstructured and irregular nature of Gaussian point clouds, it is difficult to guarantee geometric reconstruction accuracy and multi-view …

cn (code pays fourni par la source)