Publications (35)
Focus on Local Regions for Query-based Object Detection
Hongbin Xu, Yamei Xia, Shuai Zhao +1
Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges li…
Digging into Uncertainty in Self-supervised Multi-view Stereo
Hongbin Xu, Zhipeng Zhou, Yali Wang +4
Self-supervised Multi-view stereo (MVS) with a pretext task of image reconstruction has achieved significant progress recently. However, previous methods are built upon intuitions,…
A Simple Framework for 3D Occupancy Estimation in Autonomous Driving
Wanshui Gan, Ningkai Mo, Hongbin Xu +1
The task of estimating 3D occupancy from surrounding-view images is an exciting development in the field of autonomous driving, following the success of Bird's Eye View (BEV) perce…
Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors
Siqi Wei, Hongbin Xu, Feng Xiao +4
Existing approaches for unsupervised 3D point cloud segmentation predominantly rely on a purely visual similarity-based learning-by-clustering paradigm, which suffers from a fundam…
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
Zihan Su, Xuerui Qiu, Hongbin Xu +6
The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, inv…
V4d: voxel for 4d novel view synthesis
Wanshui Gan, Hongbin Xu, Yi Huang +2
Neural radiance fields have made a remarkable breakthrough in the novel view synthesis task at the 3D static scene. However, for the 4D circumstance (e.g., dynamic scene), the perf…
OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Jiazheng Xing, Hai Ci, Hongbin Xu +3
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bi…
RobustMVS: Single Domain Generalized Deep Multi-view Stereo
Hongbin Xu, Weitao Chen, Baigui Sun +2
Despite the impressive performance of Multi-view Stereo (MVS) approaches given plenty of training samples, the performance degradation when generalizing to unseen domains has not b…
B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding
Feng Xiao, Hongbin Xu, Hai Ci +1
Localizing 3D objects using natural language is essential for robotic scene understanding. The descriptions often involve multiple spatial relationships to distinguish similar obje…
GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting
Wanshui Gan, Fang Liu, Hongbin Xu +2
We introduce GaussianOcc, a systematic method that investigates the two usages of Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround vie…
4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting
Wanlin Liang, Hongbin Xu, Weitao Chen +2
3D neural style transfer has gained significant attention for its potential to provide user-friendly stylization with spatial consistency. However, existing 3D style transfer metho…
LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding
Feng Xiao, Hongbin Xu, Guocan Zhao +1
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challe…
StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
Hongbo Ma, Fei Shen, Hongbin Xu +5
The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds im…
TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting
Zhicong Wu, Hongbin Xu, Gang Xu +6
Recent advancements in Generalizable Gaussian Splatting have enabled robust 3D reconstruction from sparse input views by utilizing feed-forward Gaussian Splatting models, achieving…
Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation
Hongbin Xu, Zhipeng Zhou, Yu Qiao +2
Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multi-view stereo (MVS). However, existing methods rely on the assumptio…
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
Jiazheng Xing, Fei Du, Hangjie Yuan +7
Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and…
CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Mingye Xu, Yali Wang, Zhipeng Zhou +2
Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such ap…
ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
Hongbin Xu, Weitao Chen, Zhipeng Zhou +4
Despite recent advancements in 3D generation methods, achieving controllability still remains a challenging issue. Current approaches utilizing score-distillation sampling are hind…
Time-Frequency Mode Decomposition for Wind Turbine Vibration Monitoring under Variable Speed Operation
Wei Zhou, Wei-Jian Li, Desen Zhu +2
Wind turbine vibration monitoring under variable speed operation requires separating nonstationary rotor-order components whose frequencies and operating intervals depend on operat…
Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
Keyang Lu, Sifan Zhou, Hongbin Xu +6
Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single d…
Improving 3D Finger Traits Recognition via Generalizable Neural Rendering
Hongbin Xu, Junduan Huang, Yuer Ma +2
3D biometric techniques on finger traits have become a new trend and have demonstrated a powerful ability for recognition and anti-counterfeiting. Existing methods follow an explic…
SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation
Zisheng Chen, Chunwei Wang, Runhui Huang +6
In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understan…
StyleDyRF: Zero-shot 4D Style Transfer for Dynamic Neural Radiance Fields
Hongbin Xu, Weitao Chen, Feng Xiao +2
4D style transfer aims at transferring arbitrary visual style to the synthesized novel views of a dynamic 4D scene with varying viewpoints and times. Existing efforts on 3D style t…
From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark
Shuquan Ye, Ben Fei, Hongbin Xu +2
The Solid Electrolyte Interphase (SEI) is critical to the performance of lithium-ion batteries, yet its analysis via Operando Infrared (IR) spectroscopy remains experimentally comp…
FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation
Cui Miao, Tao Chang, Meihan Wu +4
Vision-language-action (VLA) models have significantly advanced robotic manipulation by enabling robots to interpret language instructions for task execution. However, training the…
PhysMamba: State Space Duality Model for Remote Physiological Measurement
Zhixin Yan, Yan Zhong, Hongbin Xu +4
Remote Photoplethysmography (rPPG) enables non-contact physiological signal extraction from facial videos, offering applications in psychological state analysis, medical assistance…
Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization
Hongbin Xu, Chaohui Yu, Feng Xiao +5
Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remai…
GSsplat: Generalizable Semantic Gaussian Splatting for Novel-view Synthesis in 3D Scenes
Feng Xiao, Hongbin Xu, Wanlin Liang +1
The semantic synthesis of unseen scenes from multiple viewpoints is crucial for research in 3D scene understanding. Current methods are capable of rendering novel-view images and s…
SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention
Feng Xiao, Hongbin Xu, Qiuxia Wu +1
3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objec…
CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo
Weitao Chen, Hongbin Xu, Zhipeng Zhou +4
The core of Multi-view Stereo(MVS) is the matching process among reference and source pixels. Cost aggregation plays a significant role in this process, while previous methods focu…
Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking
Ziyi Wang, Songbai Tan, Gang Xu +5
With the success of autoregressive learning in large language models, it has become a dominant approach for text-to-image generation, offering high efficiency and visual quality. H…
PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering
Zisheng Chen, Hongbin Xu, Weitao Chen +5
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled…
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
Deyun Zhang, Shijia Geng, Yang Zhou +28
The artificial intelligence (AI) system has achieved expert-level performance in electrocardiogram (ECG) signal analysis. However, in underdeveloped countries or regions where the…
Semi-supervised Deep Multi-view Stereo
Hongbin Xu, Weitao Chen, Yang Liu +5
Significant progress has been witnessed in learning-based Multi-view Stereo (MVS) under supervised and unsupervised settings. To combine their respective merits in accuracy and com…
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
Jianke Zhang, Yuanfei Luo, Yucheng Hu +6
Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe system…