no code implementations • 3 Dec 2023 • Hao Yang, Liyuan Pan, Yan Yang, Wei Liang
Then, with the guidance of degradation prior, we sparsely select restoration experts from a candidate list dynamically based on a Mixture-of-Experts (MoE) structure.
no code implementations • 20 Nov 2023 • Yan Yang, Liyuan Pan, Liu Liu
This paper introduces a self-supervised learning framework designed for pre-training neural networks tailored to dense prediction tasks using event camera data.
no code implementations • 22 Aug 2023 • Xin Duan, Yan Yang, Liyuan Pan, Xiabi Liu
With a backbone segmentation network that independently processes each image from the set, we introduce semantics from CLIP into the backbone features, refining them in a coarse-to-fine manner with three key modules: i) an image set feature correspondence module, encoding global consistent semantic information of the image set; ii) a CLIP interaction module, using CLIP-mined common semantics of the image set to refine the backbone feature; iii) a CLIP regularization module, drawing CLIP towards this co-segmentation task, identifying the best CLIP semantic and using it to regularize the backbone feature.
no code implementations • 19 Jul 2023 • Hao Yang, Liyuan Pan, Yan Yang, Richard Hartley, Miaomiao Liu
In this paper, we propose, to the best of our knowledge, the first framework that introduces the contrastive language-image pre-training framework (CLIP) to accurately estimate the blur map from a DP pair unsupervisedly.
no code implementations • ICCV 2023 • Yan Yang, Liyuan Pan, Liu Liu
Our model is a self-supervised learning framework, and uses paired event camera data and natural RGB images for training.
no code implementations • CVPR 2023 • Mengqiao Han, Liyuan Pan, Xiabi Liu
Then, with the astrocytes, we propose an AstroNet that can adaptively optimize neuron connections and therefore achieves structure learning to achieve higher accuracy and efficiency.
no code implementations • CVPR 2023 • Yan Yang, Liyuan Pan, Liu Liu, Miaomiao Liu
It estimates a disparity feature map, which is used to query a trainable kernel set to estimate a blur kernel that best describes the spatially-varying blur.
no code implementations • 30 Oct 2022 • Yan Yang, Liyuan Pan, Liu Liu, Eric A Stone
Instead, we present ISG framework that harnesses interactions among discriminative features from texture-abundant regions by three new modules: 1) a Shannon Selection module, based on the Shannon information content and Solomonoff's theory, to filter out textureless image regions; 2) a Feature Extraction network to extract expressive low-dimensional feature representations for efficient region interactions among a high-resolution image; 3) a Dual Attention network attends to regions with desired gene expression features and aggregates them for the prediction task.
1 code implementation • 23 Mar 2022 • Yan Yang, Zakir Hossain, Khandaker Asif, Liyuan Pan, Shafin Rahman, Eric Stone
De novo peptide sequencing aims to recover amino acid sequences of a peptide from tandem mass spectrometry (MS) data.
1 code implementation • 11 Oct 2021 • Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang, Robert Mahony
We provide a SHEF dataset targeted at evaluating disparity estimation algorithms and introduce a stereo disparity estimation algorithm that uses edge information extracted from the event stream correlated with the edge detected in the frame data.
1 code implementation • CVPR 2021 • Liyuan Pan, Shah Chowdhury, Richard Hartley, Miaomiao Liu, Hongguang Zhang, Hongdong Li
The heavy defocus blur in DP pairs affects the performance of matching-based depth estimation approaches.
no code implementations • CVPR 2020 • Liyuan Pan, Miaomiao Liu, Richard Hartley
Then, we consider the special case of image blur caused by high dynamics in the visual environments and show that including the blur formation in our model further constrains flow estimation.
no code implementations • 6 Oct 2019 • Liyuan Pan, Yuchao Dai, Miaomiao Liu, Fatih Porikli, Quan Pan
Under our model, these three tasks are naturally connected and expressed as the parameter estimation of 3D scene structure and camera motion (structure and motion for the dynamic scenes).
no code implementations • CVPR 2019 • Liyuan Pan, Richard Hartley, Miaomiao Liu, Yuchao Dai
The image motion blurring process is generally modelled as the convolution of a blur kernel with a latent image.
1 code implementation • 12 Mar 2019 • Liyuan Pan, Richard Hartley, Cedric Scheerlinck, Miaomiao Liu, Xin Yu, Yuchao Dai
Based on the abundant event data alongside a low frame rate, easily blurred images, we propose a simple yet effective approach to reconstruct high-quality and high frame rate sharp videos.
no code implementations • 1 Mar 2019 • Liyuan Pan, Yuchao Dai, Miaomiao Liu
Camera shake during exposure is a major problem in hand-held photography, as it causes image blur that destroys details in the captured images.~In the real world, such blur is mainly caused by both the camera motion and the complex scene structure.~While considerable existing approaches have been proposed based on various assumptions regarding the scene structure or the camera motion, few existing methods could handle the real 6 DoF camera motion.~In this paper, we propose to jointly estimate the 6 DoF camera motion and remove the non-uniform blur caused by camera motion by exploiting their underlying geometric relationships, with a single blurry image and its depth map (either direct depth measurements, or a learned depth map) as input.~We formulate our joint deblurring and 6 DoF camera motion estimation as an energy minimization problem which is solved in an alternative manner.
1 code implementation • CVPR 2019 • Liyuan Pan, Cedric Scheerlinck, Xin Yu, Richard Hartley, Miaomiao Liu, Yuchao Dai
In this paper, we propose a simple and effective approach, the \textbf{Event-based Double Integral (EDI)} model, to reconstruct a high frame-rate, sharp video from a single blurry frame and its event data.
no code implementations • 26 Nov 2018 • Liyuan Pan, Richard Hartley, Miaomiao Liu, Yuchao Dai
The image blurring process is generally modelled as the convolution of a blur kernel with a latent image.
no code implementations • 27 Nov 2017 • Liyuan Pan, Yuchao Dai, Miaomiao Liu, Fatih Porikli
In this paper, we propose to tackle the problem of depth map completion by jointly exploiting the blurry color image sequences and the sparse depth map measurements, and present an energy minimization based formulation to simultaneously complete the depth maps, estimate the scene flow and deblur the color images.
no code implementations • CVPR 2017 • Liyuan Pan, Yuchao Dai, Miaomiao Liu, Fatih Porikli
Unlike the existing approach [31] which used a pre-computed scene flow, we propose a single framework to jointly estimate the scene flow and deblur the image, where the motion cues from scene flow estimation and blur information could reinforce each other, and produce superior results than the conventional scene flow estimation or stereo deblurring methods.