1.2k citations · 1.5k across the 81 of their papers we have counts for
20 papers · 1 filter
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Zhehan Kan, Ce Zhang, Zihan Liao +7
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing sig…
Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection
Yifan Wang, Xiaochen Yang, Fanqi Pu +2
Monocular 3D object detection has attracted great attention due to simplicity and low cost. Existing methods typically follow conventional 2D detection paradigms, first locating ob…
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors
Fanqi Pu, Yifan Wang, Jiru Deng +1
Perspective projection has been extensively utilized in monocular 3D object detection methods. It introduces geometric priors from 2D bounding boxes and 3D object dimensions to red…
Improving Consistency in Diffusion Models for Image Super-Resolution
Junhao Gu, Peng-Tao Jiang, Hao Zhang +4
Recent methods exploit the powerful text-to-image (T2I) diffusion models for real-world image super-resolution (Real-ISR) and achieve impressive results compared to previous models…
Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation
Xiaoyu Jin, Zunnan Xu, Mingwen Ou +1
Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining…
FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant
Zhengchao Huang, Bin Xia, Zicheng Lin +3
The rapid advancement of deepfake technologies has sparked widespread public concern, particularly as face forgery poses a serious threat to public information security. However, t…
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
Xinyi Zhang, Qiqi Bao, Qinpeng Cui +2
Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter…
GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution
Jintong Hu, Bin Xia, Bin Chen +2
Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extra…
LLM-Empowered State Representation for Reinforcement Learning
Boyuan Wang, Yun Qu, Yuhang Jiang +4
Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurat…
Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields
Jintong Hu, Siyan Chen, Zhiyi Pan +2
Precise segmentation of medical images is fundamental for extracting critical clinical information, which plays a pivotal role in enhancing the accuracy of diagnoses, formulating e…
BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network
Zongkai Zhang, Zidong Xu, Wenming Yang +2
Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of edge devices. Binarized Neural Networks (BNN) offer substantially reduced computat…
Bilateral Event Mining and Complementary for Event Stream Super-Resolution
Zhilin Huang, Quanmin Liang, Yijie Yu +5
Event Stream Super-Resolution (ESR) aims to address the challenge of insufficient spatial resolution in event streams, which holds great significance for the application of event c…
Motion-aware Latent Diffusion Models for Video Frame Interpolation
Zhilin Huang, Yijie Yu, Ling Yang +6
With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For t…
OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering
Jingrui Ye, Zongkai Zhang, Yujiao Jiang +3
Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unob…
VmambaIR: Visual State Space Model for Image Restoration
Yuan Shi, Bin Xia, Xiaoyu Jin +5
Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks…
Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes
Siang Chen, Wei Tang, Pengwei Xie +2
Fast and robust object grasping in clutter is a crucial component of robotics. Most current works resort to the whole observed point cloud for 6-Dof grasp generation, ignoring the…
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
Jiaqi Lin, Zhihao Li, Xiao Tang +8
Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-…
DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication
Yanjun Liu, Wenming Yang, Qingmin Liao
Finger vein authentication, recognized for its high security and specificity, has become a focal point in biometric research. Traditional methods predominantly concentrate on vein…
LLMRA: Multi-modal Large Language Model based Restoration Assistant
Xiaoyu Jin, Yuan Shi, Bin Xia +1
Multi-modal Large Language Models (MLLMs) have a significant impact on various tasks, due to their extensive knowledge and powerful perception and generation capabilities. However,…
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
Hongbo Kang, Yong Wang, Mengyuan Liu +4
Previous probabilistic models for 3D Human Pose Estimation (3DHPE) aimed to enhance pose accuracy by generating multiple hypotheses. However, most of the hypotheses generated devia…