no code implementations • 18 Apr 2025 • Yan Shi, Qingdong He, Yijun Liu, Xiaoyu Liu, Jingyong Su
To overcome the high parameter counts and computational inefficiency of standard KANs, we develop Efficient-KANs in the PointKAN-elite variant, which significantly reduces parameters while maintaining accuracy.
no code implementations • 12 Mar 2025 • Haoxuan Wang, Jinlong Peng, Qingdong He, Hao Yang, Ying Jin, Jiafu Wu, Xiaobin Hu, Yanjie Pan, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang
With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing.
no code implementations • 9 Mar 2025 • Yanjie Pan, Qingdong He, Zhengkai Jiang, Pengcheng Xu, Chaoyi Wang, Jinlong Peng, Haoxuan Wang, Yun Cao, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang
Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control.
no code implementations • 4 Dec 2024 • Qingdong He, Jinlong Peng, Pengcheng Xu, Boyuan Jiang, Xiaobin Hu, Donghao Luo, Yong liu, Yabiao Wang, Chengjie Wang, Xiangtai Li, Jiangning Zhang
To enhance the controllability of text-to-image diffusion models, current ControlNet-like models have explored various control signals to dictate image attributes.
no code implementations • 24 Nov 2024 • Pengcheng Xu, Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Charles Ling, Boyu Wang
Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents.
2 code implementations • 15 Nov 2024 • Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Chengming Xu, Jinlong Peng, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Yanwei Fu
Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios.
Ranked #1 on
Virtual Try-on
on VITON-HD
1 code implementation • 12 Nov 2024 • Jiaxuan Chen, Bo Zhang, Qingdong He, Jinlong Peng, Li Niu
Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image.
1 code implementation • 4 Nov 2024 • Yijun Liu, Jiequan Cui, Zhuotao Tian, Senqiao Yang, Qingdong He, Xiaoling Wang, Jingyong Su
We observe that, with the cross-entropy loss, model predictions are optimized to align with the corresponding labels via increasing logit magnitude or refining logit direction.
1 code implementation • 13 Sep 2024 • Haoxuan Wang, Qingdong He, Jinlong Peng, Hao Yang, Mingmin Chi, Yabiao Wang
However, its performance is hindered by its neck feature fusion mechanism, which causes the quadratic complexity and the limited guided receptive fields.
1 code implementation • 24 Aug 2024 • Ying Jin, Jinlong Peng, Qingdong He, Teng Hu, Hao Chen, Jiafu Wu, Wenbing Zhu, Mingmin Chi, Jun Liu, Yabiao Wang, Chengjie Wang
In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part.
1 code implementation • 15 Jul 2024 • Mufeng Yao, Jinlong Peng, Qingdong He, Bo Peng, Hao Chen, Mingmin Chi, Chao Liu, Jon Atli Benediktsson
To address these issues, we propose the Motion Mamba Module, which explores both local and global motion features through cross-correlation and bi-directional Mamba Modules for better motion modeling.
1 code implementation • 5 Jun 2024 • Jiangning Zhang, Haoyang He, Zhenye Gan, Qingdong He, Yuxuan Cai, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong liu
This paper addresses this issue by proposing a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework that is highly extensible for new methods.
1 code implementation • 30 May 2024 • Kai Wu, Boyuan Jiang, Zhengkai Jiang, Qingdong He, Donghao Luo, Shengzhi Wang, Qingwen Liu, Chengjie Wang
Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models.
no code implementations • 28 May 2024 • Sihe Zhang, Qingdong He, Jinlong Peng, Yuxi Li, Zhengkai Jiang, Jiafu Wu, Mingmin Chi, Yabiao Wang, Chengjie Wang
To mitigate this issue, we introduce a novel setting for low-quality image retrieval, and propose an Adaptive Noise-Based Network (AdapNet) to learn robust abstract representations.
no code implementations • 24 May 2024 • Qingdong He, Jiangning Zhang, Jinlong Peng, Haoyang He, Xiangtai Li, Yabiao Wang, Chengjie Wang
Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational resources.
no code implementations • 24 May 2024 • Hanchen Tai, Qingdong He, Jiangning Zhang, Yijie Qian, Zhenyu Zhang, Xiaobin Hu, Xiangtai Li, Yabiao Wang, Yong liu
This framework is designed to perform understanding tasks for any 3D scene without requiring prior knowledge of the scene.
no code implementations • 17 Apr 2024 • Qiangang Du, Jinlong Peng, Changan Wang, Xu Chen, Qingdong He, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
Next, a shape-aware and a brightness-aware module are designed to improve the capacity for representation learning.
no code implementations • 17 Apr 2024 • Qiangang Du, Jinlong Peng, Xu Chen, Qingdong He, Liren He, Qiang Nie, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang
In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization.
3 code implementations • 9 Apr 2024 • Haoyang He, Yuhu Bai, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie
Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches.
no code implementations • 11 Mar 2024 • Qingdong He, Jinlong Peng, Zhengkai Jiang, Xiaobin Hu, Jiangning Zhang, Qiang Nie, Yabiao Wang, Chengjie Wang
On top of that, PointSeg can incorporate with various foundation models and even surpasses the specialist training-based methods by 3. 4$\%$-5. 4$\%$ mAP across various datasets, serving as an effective generalist model.
1 code implementation • 21 Jan 2024 • Qingdong He, Jinlong Peng, Zhengkai Jiang, Kai Wu, Xiaozhong Ji, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Mingang Chen, Yunsheng Wu
3D open-vocabulary scene understanding aims to recognize arbitrary novel categories beyond the base label space.
no code implementations • 9 Jun 2020 • Qingdong He, Zhengning Wang, Hao Zeng, Yijun Liu, Shuaicheng Liu, Bing Zeng
After aligning the interior points with fused features, the proposed network refines the prediction in a more accurate manner and encodes the whole box in a novel compact method.
no code implementations • 7 Jun 2020 • Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, Yijun Liu
Accurate 3D object detection from point clouds has become a crucial component in autonomous driving.
Ranked #1 on
3D Object Detection
on KITTI Pedestrians Hard