6 citations · 17 across the 18 of their papers we have counts for
9 papers · 1 filter
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
Kang Liao, Yihang Luo, Xiao-Ming Wu +7
We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation and reconstruction without relying on…
VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms
Xiao-Ming Wu, Bin Fan, Kang Liao +6
Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding from Vision-Language Models for gen…
ProEdit: Inversion-based Editing From Prompts Done Right
Zhi Ouyang, Dian Zheng, Xiao-Ming Wu +4
Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions. Existing methods typically inject source image in…
Panorama Generation From NFoV Image Done Right
Dian Zheng, Cheng Zhang, Xiao-Ming Wu +4
Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the…
PixelFade: Privacy-preserving Person Re-identification with Noise-guided Progressive Replacement
Delong Zhang, Yi-Xing Peng, Xiao-Ming Wu +2
Online person re-identification services face privacy breaches from potential data leakage and recovery attacks, exposing cloud-stored images to malicious attackers and triggering…
Single-View Scene Point Cloud Human Grasp Generation
Yan-Kang Wang, Chengyi Xing, Yi-Lin Wei +2
In this work, we explore a novel task of generating human grasps based on single-view scene point clouds, which more accurately mirrors the typical real-world situation of observin…
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Dian Zheng, Xiao-Ming Wu, Shuzhou Yang +3
Universal image restoration is a practical and potential computer vision task for real-world applications. The main challenge of this task is handling the different degradation dis…
DiffuVolume: Diffusion Model for Volume based Stereo Matching
Dian Zheng, Xiao-Ming Wu, Zuhao Liu +2
Stereo matching is a significant part in many computer vision tasks and driving-based applications. Recently cost volume-based methods have achieved great success benefiting from t…
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training
Xiao-Ming Wu, Dian Zheng, Zuhao Liu +1
Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradient…