Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks182 from public data
- PraNet: Parallel Reverse Attention Network for Polyp Segmentation1,966
Quantitative and qualitative evaluations on five challenging datasets across six metrics show that the PraNet improves the segmentation accuracy significantly, and presents a number of advantages in terms of generalizability, and real-time segmentation efficiency.
- Triplet Loss in Siamese Network for Object Tracking647
A novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training.
- Video Salient Object Detection via Fully Convolutional Networks642
A novel data augmentation technique that simulates video training data from existing annotated image data sets, which enables the deep video saliency network to learn diverse saliency information and prevents overfitting with the limited number of training videos.
- Learning Human-Object Interactions by Graph Parsing Neural Networks596
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos with the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end.
- 543
- See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks537
This work introduces a novel network, called as CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view and proposes a unified and end-to-end trainable framework where different co-att attention variants can be derived for mining the rich context within videos.
- 510
- Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection492
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvL STM), which achieves state-of-the-art results on two popular benchmarks, well demonstrating its superior performance and high applicability.
- 472
- Human-Aware Motion Deblurring403
A human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG) humans based on a triple-branch encoder-decoder architecture that performs favorably against the state-of-the-art motion deblurred methods, especially in capturing semantic details.
- 395
- 384
- 348
- 342
- RGB-D salient object detection: A survey322
This paper provides a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail, and investigates the ability of existing models to detect salient objects.
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model311
This work introduces a new benchmark for predicting human eye movements during dynamic scene free-viewing, and proposes a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning.
- Video Object Segmentation with Episodic Graph Memory Networks303
This work exploits an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges and yields a neat yet principled framework, which can generalize well both one-shot and zero-shot video object segmentation tasks.
- Siamese Network for RGB-D Salient Object Detection and Beyond250
The proposed JL-DCF module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery.
- 242
- 241
- 234
- 218
- 208
- 205
- Learning Video Object Segmentation From Unlabeled Videos184
A unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities is introduced that can help advance understanding of visual patterns in VOS and significantly reduce annotation burden.
- Full-duplex strategy for video object segmentation180
This work introduces a relational cross-attention module (RCAM) to achieve bidirectional message propagation across embedding sub-spaces and adopts a biddirectional purification module after the RCAM to improve the model’s robustness and update inconsistent features from the spatiotemporal embeddings.
- Exposure Fusion Using Boosting Laplacian Pyramid175
This paper proposes a new exposure fusion approach for producing a high quality image result from multiple exposure images based on the local weight and global weight by considering the exposure quality measurement between different exposure images, and the just noticeable distortion-based saliency weight is developed.
- Structured Scene Memory for Vision-Language Navigation171
This work proposes a crucial architecture, called Structured Scene Memory (SSM), which is compartmentalized enough to accurately memorize the percepts during navigation and serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
- Re-thinking Co-Salient Object Detection170
A novel CoEG-Net is proposed that augments the authors' prior model EGNet with a co-attention projection strategy to enable fast common information learning and fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability.
- 161
- 161
- Referring Multi-Object Tracking156
This paper proposes a new and general referring understanding task, termed referring multi-object tracking (RMOT), whose core idea is to employ a language expression as a semantic cue to guide the prediction of multi- object tracking.
- 156
- 155
- IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection150
IS-Fusion is proposed, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information and outperforms all the published multimodal works to date.
- 147
- 144
- Learning Compositional Neural Information Fusion for Human Parsing141
This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing, formulate the approach as a neural information fusion framework that is extensively evaluated on four popular datasets.
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Deep Cropping via Attention Box Prediction and Aesthetics Assessment120
A neural network is designed that has two branches for predicting attention bounding box and analyzing aesthetics, respectively that avoids repeated feature computation and leading to higher computation efficiency in photo cropping.
- A Unified Object Motion and Affinity Model for Online Multi-Object Tracking118
This paper proposes a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both objectMotion and affinity measure.
- ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection115
A new unsupervised point cloud pre-training framework, called ProposalContrast, that learns robust 3D representations by contrasting region proposals that optimizes with both inter-cluster and inter-proposal separation.
- Hierarchical Human Parsing With Typed Part-Relation Reasoning115
This work seeks to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures by assimilating generic message-passing networks with their edge-typed, convolutional counterparts and lays the foundation for more sophisticated and flexible human relation patterns of reasoning.
- 113
- Visual Tracking Using Strong Classifier and Structural Local Sparse Descriptors109
A boosting-based strong classifier for robust visual tracking using a discriminative appearance model and a structural reconstruction error based weight computation method are proposed to adjust the classification score of each candidate for more precise tracking results.
- OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation100
This work breaks up the previous offline belief and proposes a simple yet effective online model using explicit query propagation, named OnlineRefer, that leverages target cues that gather semantic information and position prior to improve the accuracy and ease of referring predictions for the current frame.
- CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers98
A compact latent network is proposed to quickly adjust the tracking model to adapt to new scenes and a new training approach based on a diverse sample mining strategy is designed to further improve the discrimination ability of the compact latent network.
- 95
- Learning to Fuse Asymmetric Feature Maps in Siamese Trackers94
The asymmetric convolution (ACM) is proposed, which learns to better capture the se-mantic correlation information in offline training on large-scale data and can easily be integrated into existing Siamese trackers based on DW-XCorr or XCorr.
- 94
- Intrinsic Image Decomposition Using Optimization and User Scribbles91
This paper presents a novel high-quality intrinsic image recovery approach using optimization and user scribbles that achieves a better recovery result of intrinsic reflectance and illumination components than the previous approaches.
- Active Visual Information Gathering for Vision-Language Navigation89
This work proposes an end-to-end framework for learning an exploration policy that decides i) when and where to explore, ii) what information is worth gathering during exploration, and iii) how to adjust the navigation decision after the exploration.
- 87
- Interactive Segmentation Using Constrained Laplacian Optimization87
This approach is the first to incorporate the normalized cuts and graph cuts algorithms into a unified energy optimization framework and achieves better performance of both boundary recall and error rate than the existing state-of-the-art approaches.
- Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation86
This work describes an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa.
- 82
- 80
- 79
- Digital holographic deep learning of red blood cells for field-portable, rapid COVID-19 screening78
This is the first report of digital holographic microscopy for rapid screening of red blood cells for active infection of COVID-19 and the proposed system may be beneficial for under-resourced healthcare systems.
- 78
- A deep Coarse-to-Fine network for head pose estimation from synthetic data76
This paper designs a rendering pipeline to synthesize realistic head images and generates an annotated dataset with a collection of 310k head poses, and proposes a deep neural network following the Coarse-to-Fine strategy to estimate head poses.
- Modality Synergy Complement Learning with Cascaded Aggregation for Visible-Infrared Person Re-Identification74
A novel framework to synergize two modalities to construct diverse representations of identity-discriminative semantics and less noise is proposed, and a Cascaded Aggregation strategy for fine-grained optimization of the feature distribution, which progressively aggregates feature embeddings from the subclass, intra-class, and inter-class.
- 74
- 72
- 72
- Depth-Aware Image Seam Carving71
A novel depth-aware single image seam carving approach by taking advantage of the modern depth cameras such as the Kinect sensor, which captures the RGB color image and its corresponding depth map simultaneously, and an efficient JND-based significant computation approach using the multiscale graph cut based energy optimization.
- 69
- Gradient based image completion by solving the Poisson equation69
A new patch-matching criterion is developed in the approach to govern the completion of gradient maps in the removed area, and both the gradient and the color information are incorporated in this new criterion, so a better image completion result is obtained.
- Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback64
Experimental results demonstrate that the proposed UMed-LVLM significantly outperforms existing Med-LVLMs in identifying and understanding medical abnormalities, achieving a 58% improvement over the baseline, and shows that enhancing the abnormality detection capabilities of Med-LVLMs significantly improves their understanding of medical images and generalization capability.
- 62
- TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning58
This work introduces a powerful 3D lane detector and an improved 2D traffic element detector to extend the upper limit of topology performance and proposes TopoMLP, a simple yet high-performance pipeline for driving topology reasoning.
- 57
- Generalized Pooling for Robust Object Tracking56
This work presents a more generalized feature pooling method for visual tracking by utilizing the probabilistic function to model the statistical distribution of sparse codes and introduces the Fisher vector to derive a more compact and discriminative representation for sparse codes of the visual target.
- 53
- Gradient Based Image Completion by Solving Poisson Equation53
A novel image completion algorithm is proposed for removing significant objects from natural images or photographs by incorporating the gradient and color information together together to determine the target patch.
- 51
- 51
- 50
- 50
- Super-Trajectory for Video Segmentation50
A novel semi-supervised video segmentation approach based on an efficient video representation, called as “super-trajectory”, which is capable of distinguishing the target objects from complex backgrounds and even reidentifying them after occlusions.
- Robust Match Fusion Using Optimization48
This algorithm is the first patch-based exposure fusion work to preserve the moving objects of dynamic scenes that does not need the registration process of different exposure images, and it achieves visually pleasing fusion results without ghosting artifacts.
- Parallel and efficient approximate nearest patch matching for image editing applications46
A novel GPU-based patch matching method which efficiently finds approximate nearest neighbor correspondences for patches between images by reducing the search space of patch direction by estimating a coherent feature direction field for each image and computing the similarity between patches with a direction-aware alignment scheme.
- High-Order Energies for Stereo Segmentation46
This approach is the first one to formulate the problem of stereo segmentation as a high-order energy optimization problem, which simultaneously segments the foreground objects in left and right images using the proposed high- order potential function.
- A Color Image Encryption Algorithm Based on Magic Cube Transformation and Modular Arithmetic Operation44
A color image encryption algorithm based on magic cube transformation and a new modular arithmetic operation is designed and a natural number chaotic sequence is created with the secret key to increase the security for decryption.
- Facial landmark detection by semi-supervised deep learning43
A semi-supervised facial landmark detection algorithm (SEMI) based on convolutional neural network (CNN), which can detect facial components and landmarks simultaneously simultaneously is proposed, which solves the occlusion problem of large area by detecting the visible facial components while existing face detectors failed to detect faces.
- 40
- Video Supervoxels Using Partially Absorbing Random Walks39
This paper presents the novel video supervoxel generation algorithm using partially absorbing random walks to get more accurate supervoxels in regions with complex textures or weak boundaries and builds a novel Laplacian optimization structure using two adjacent frames to make the approach more efficient.
- 36
- Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network35
A new Direction-aware Cumulative Convolution Network (DaCCN), which improves the depth feature representation in two aspects and proposes a direction-aware module, which can learn to adjust the feature extraction in each direction, facilitating the encoding of different types of information.
- Scene text recognition using residual convolutional recurrent neural network33
A residual convolutional recurrent neural network is proposed for solving the task of scene text recognition and VGG and ResNet are introduced to train these different deep models and obtain the encoding information of images.
- 30
- Robust Shadow Detection by Exploring Effective Shadow Contexts29
This paper proposes a novel encoder-decoder style of shadow detection method where ECA acts as the main building block of the encoder to extract strong feature representations and the guidance to the classification process of the decoder.
- Superpixel Optimization Using Higher Order Energy29
A novel superpixel extraction algorithm using a higher order energy optimization framework is proposed in this paper that generates better results with well-aligned boundaries and homogeneous effects than the existing superpixel algorithms.
- Real-time feature-aware video abstraction28
A novel feature-aware rendering system that automatically abstracts videos and images with the goal of improving the effectiveness of imagery for visual communication tasks and uses a feature flow-guided anisotropic edge detection filter to enhance regions of high contrast.
- Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving27
A Multi-modal Single Shot Grounding approach with an effective token fusion strategy that jointly learns the LiDAR-based object detector with the language features and predicts the targeted region directly from the detector without any post-processing.
- 27
- 26
- 26
- Exposing the Self-Supervised Space-Time Correspondence Learning via Graph Kernels25
The VideoHiGraph is proposed, a space-time correspondence framework based on a learnable graph kernel that achieves superior performance and demonstrates its robustness across the benchmark of label propagation tasks involving objects, semantic parts, keypoints, and instances.
- A Retrospective Comparison of Deep Learning to Manual Annotations for Optic Disc and Optic Cup Segmentation in Fundus Photographs25
The potential of the deep learning system to assist ophthalmologists in analyzing OD and OC segmentation and discriminating glaucoma from nonglaucomA subjects based on CDR calculations is demonstrated.
- Real-time saliency-aware video abstraction24
This paper proposes a progressive abstraction method based on a region-of-interest function derived from an elaborate perception model which describes the flow of salient features of the input image and can be executed automatically in real time on the GPU, without requiring any user intervention.
- Fast approximation of trilateral filter for tone mapping using a signal processing approach24
A novel fast approximation of the trilateral filter for high dynamic range (HDR) image tone mapping using a signal processing approach and the experimental results show satisfactory performancce.
- 22
- 21
- One-Stage Anchor-Free 3D Vehicle Detection from LiDAR Sensors21
This work proposes a one-stage, anchor-free 3D vehicle detection algorithm based on LiDAR point clouds that combines SmoothL1 loss and IoU (Intersection over Union) loss, and applies angle regression labels, which achieve high average orientation similarity (AOS) without any direction classification tricks.
- Extreme Points Derived Confidence Map as a Cue for Class-Agnostic Interactive Segmentation Using Deep Neural Network21
A novel approach to compute a confidence map from extreme points that quantitatively encodes the priors derived fromextreme points is proposed and suggested that models trained using cues can be used to generate reliable training data.
- 21
- 20
- Re-texturing by Intrinsic Video20
This approach begins with indicating the regions of interests by contour-aware layer segmentation, and then, the intrinsic video within the segmented region is recovered by the authors' weighted energy optimization, which can produce high quality video re-texturing results with preserving the lighting and shading effect of the original video.
- 19
- Interactive image/video retexturing using GPU parallelism19
This paper presents an interactive retexturing approach that preserves similar underlying texture distortion between the original and retextured images/videos via real-time feedback interaction and feature-guided texture distortion optimization using CUDA parallelism.
- Detail-preserving exposure fusion using subband architecture18
Given a sequence of different exposures, the Quadrature Mirror Filter based subband architecture is first employed to decompose the original sequence into different frequency subbands, and the importance weight maps according to the image appearance measurements, such as exposure, contrast, and saturation are computed.
- 17
- A stable long-term object tracking method with re-detection strategy16
This work proposed a long-term tracking strategy to deal with the occlusion, out-of-plane rotation, and the confusing non-target object, and introduced to adopt both the maximum response criterion and the APCE criterion to judge the performance of the tracker in time.
- 16
- Completion-based texture design using deformation16
This paper presents a novel approach for designing a variety of large textures from a single small sample texture using a set of chaotic-based transformation operations, which shows particular strength in generating a large variety of texturesfrom a single sample texture while avoiding highly repetitive patterns.
- 15
- High dynamic range image tone mapping and retexturing using fast trilateral filtering15
Using fast trilateral filtering the authors present a novel tone mapping and retexturing method for high dynamic range (HDR) images that is based on fast bilateral filtering and two newly developed filters: the quasi-Cauchy function kernel filter and the fourth degree Taylor polynomial kernel filter.
- Decoupling the Curve Modeling and Pavement Regression for Lane Detection14
This paper proposes a new approach to the lane detection task by decomposing it into two parts: curve modeling and ground height regression, which uses a parameterized curve to represent lanes in the BEV space to reflect the original distribution of lanes.
- 14
- Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation13
A novel prompt optimization framework, designed to rephrase a simple user prompt into a sophisticated prompt to a text-to-image model, and employ the large vision language models (LVLMs) as the solver to rewrite the user prompt, and concurrently, employ LVLMs as a reward model to score the aesthetics and alignment of the images generated by the optimized prompt.
- Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving13
This work proposes a novel task, called generalized few-shot 3D object detection, where the authors have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes, and proposes a sample adaptive balance loss to alleviate the issue of long-tailed data distribution in autonomous driving scenarios.
- 13
- Accurate Normal and Reflectance Recovery Using Energy Optimization13
Experimental results show that the proposed approach to accurately estimate surface normal and reflectance of an object from an input image sequence yields more realistic normal map and accurate albedo map than the state-of-the-art uncalibrated photometric stereo algorithms.
- AtelierM++: a fast and accurate marbling system13
AtelierM++, a new interactive marbling image rendering system which allows artists to create marbling textures with real-time visual feedback on mega-pixel sized images, is presented.
- Learning Disentanglement with Decoupled Labels for Vision-Language Navigation12
A new Disentanglement framework with Decou-pled Labels (DDL) for VLN is proposed, achieving better performance than previous state-of-the-art methods and enhancing the generalization ability.
- Multi-attention deep reinforcement learning and re-ranking for vehicle re-identification12
This paper proposes a Multi-Attention Deep Reinforcement Learning (MADRL) model to focus on multi-attentional subregions that spreading randomly in the image, and extract the discriminative features for the Re-ID task.
- TrajDiff: End-to-end Autonomous Driving without Perception Annotation11
TrajDiff, a Trajectory-oriented BEV Conditioned Diffusion framework that establishes a fully perception annotation-free generative method for end-to-end autonomous driving, and Trajectory-oriented BEV Diffusion Transformer (TB-DiT), which leverages ego-state information and the predicted TrajBEV features to directly generate diverse yet plausible trajectories, eliminating the need for handcrafted motion priors.
- 11
- 11
- Diffusion Model with Representation Alignment for Protein Inverse Folding10
A novel method that leverages diffusion models with representation alignment (DMRA) is proposed, which enhances diffusion-based inverse folding by proposing a shared center that aggregates contextual information from the entire protein structure and selectively distributes it to each residue.
- Segmentation Using SubMarkov Random Walk10
This paper unify the proposed subRW and the other popular random walk algorithms, and design a subRW algorithm with label prior to solve the segmentation problem of objects with thin and elongated parts.
- 9
- Video person re-identification with global statistic pooling and self-attention distillation9
A novel Global Statistic Pooling network (GSPnet) is proposed which takes full advantage of the second-order information for enhancing modeling capability, and a multi-level self-attention distillation training scheme, which squeezes the knowledge learned in the deeper portion of the networks into the shallow ones.
- Deep understanding of big geospatial data for self-driving cars9
Big geospatial data understanding is helpful in acquiring travel behavior, vehicle mobility, traffic flow, and nearby environment in self-driving cars.
- 8
- High-speed video salient object detection with temporal propagation using correlation filter8
A high-speed video salient object detection method at 0.5s each frame, which integrates the spatial saliency by robust minimum barrier distance and boundary contrast cue with temporal saliency information from motion field and incorporates correlation filters to keep the saliency consistency between neighboring frames.
- Structured-Patch Optimization for Dense Correspondence8
A new method to compute the dense correspondences between two images by using the energy optimization and the structured patches using the property of the sparse feature and the principle that nearest sub-scenes and neighbors are much more similar is presented.
- 8
- 7
- Fast and Reliable Mouse Picking Using Graphics Hardware7
A fast and reliable mouse picking algorithm using graphics hardware for 3D triangular scenes using a multi-layer rendering algorithm to perform the picking operation in linear time complexity is proposed.
- 7
- 6
- Deformation-based interactive texture design using energy optimization6
Experimental results demonstrate that the proposed technique can be used for designing a large variety of versatile textures from a single small sample texture, increasing or decreasing the density of texture elements, as well as for synthesizing textures from multiple sources.
- 5
- 5
- 5
- Diffusion-based saliency detection with optimal seed selection scheme5
A linear model is learned to predict the confidence of assigning a superpixel to the foreground or to the background, and then an adaptive thresholding method is adopted to generate reliable foreground and background seeds, from which the saliency value is propagated in the diffusion procedure.
- Efficient image/video retexturing using parallel bilateral grids5
This paper proposes to utilize corner features to naturally discover the underlying texture distortion existed in the original images, and facilitates the HDR image/video retexturing via real-time bilateral grid and feature-guided texture distortion optimization on GPU-CUDA platform.
- Modality Confusion Learning: A Versatile Framework for Visible-Infrared Re-identification4
This work proposes an end-to-end Modality Confusion Learning Network+ (MCLNet+), which ensures the extracted features are related to the identity and reliable beyond the different modalities, and outperforms the existing state-of-the-art performances on both visible-infrared recognition tasks.
- 4
- 4
- Dynamic Textures Using Wavelet Analysis4
A new dynamic texture technique by using the new mixed auto-regressive moving average exogenous (MARMAX) model in the wavelet domain, which can synthesize long dynamic texture videos with temporal coherency.
- A unified framework for designing textures using energy optimization3
The proposed interactive scheme has the ability to globally change the visual properties of texture elements, and locally change texture elements with little user interaction, and can help design a large variety of textures from a small example.
- 3
- Simple and Fast Terrain Rendering Using Graphics Hardware3
This approach sufficiently exploits both the spatial and temporal coherence of terrain geometry and reduces the bandwidth requirements and can achieve very high frame rates especially when a player wanders through a valley in games or other applications.
- Sim4Seg: Boosting Multimodal Multi-disease Medical Diagnosis Segmentation with Region-Aware Vision-Language Similarity Masks2
A medical vision-language task named Medical Diagnosis Segmentation (MDS), which aims to understand clinical queries for medical images and generate the corresponding segmentation masks as well as diagnostic results, and proposes Sim4Seg, a novel framework that improves the performance of diagnosis segmentation by taking advantage of the Region-Aware Vision-Language Similarity to Mask (RVLS2M) module.
- AdaOcc: Adaptive Forward View Transformation and Flow Modeling for 3D Occupancy and Flow Prediction2
The innovative approach involves a dual-stage framework that enhances 3D occupancy and flow predictions by incorporating adaptive forward view transformation and flow modeling, validating the potential of the method in advancing autonomous car perception systems.
- 2
- 2
- 2
- 2
- 2
- Fast Shape-Simplifying Image Abstraction Using Graphics Hardware2
This paper presents a new GPU-based method for creating abstracted representations of photographs based on the constrained mean curvature flow and the Shock filter, which outperforms the CPU-based one with two magnitudes of speedup.
- 1
- Reducing CT Metal Artifacts by Learning Latent Space Alignment with Gemstone Spectral Imaging Data1
The Latent Gemstone Spectral Imaging (GSI) Alignment Framework is introduced, which effectively reduces metal artifacts while avoiding the introduction of noise information into CT sequences, and greatly enhances the readability of CT slices.
- 1
- Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion1
This paper proposes a Hybrid Priors Diffsion model, which explicitly and implicitly incorporates multi-view priors as conditions to enhance the status consistency of the generated multi-view portraits.
- Editorial: Booming of Neural Networks and Learning Systems1
As you open this January issue of the IEEE Transactions on Neural Networks and Learning Systems (TNNLS), the author is very delighted and honored to report several key metrics of IEEE TNNLS to the community.
- 1
- 1
- HDR IMAGE RERENDERING USING GPU-BASED PROCESSING1
This paper proposes the graphics processing units (GPU)-accelerated high dynamic range (HDR) image rerendering using revisited NLM processing in parallel on GPU-CUDA platform, to reproduce the realistic rendering of HDR images with retexturing and transparent/translucent effects.
- 1
- 1
- Feature-Based Texture Design Using Deformation Techniques1
A novel feature-based texture design scheme using deformation techniques that has the ability to design a variety of versatile textures from a single small sample texture by measuring the structural similarity.
- Method of texture segmentation based on wavelet-transform and GMRF1
The present approach shows visible improvements both in reducing the segmentation error and in improving the precision, comparing to the method which is proposed in the paper.
- –
- Prior Metadata-Driven RAW Reconstruction: Eliminating the Need for Per-Image Metadata–
This work proposes using Prior Meta as a reference to reconstruct the RAW data instead of relying on per-image metadata, and achieves comparable, and even better, performance than RAW reconstruction methods based on metadata.
- –
- GPU-ACCELERATED IMAGE RETEXTURING IN GRADIENT DOMAIN–
This paper presents the novel GPU-accelated image retexturing approach for both high and low dynamic range images using the authors' newly invented fast NLM filtering, integrating the fast Maclaurin polynomial kernel filter and the latest GPU-CUDA acceleration.
- Motion texture using symmetric property and graphcut algorithm–
A novel motion texture approach is presented for synthesizing long character motion (e.g., kungfu) that is similar to the original short input motion that can be patched together like the image texture synthesis method using graphcut algorithm, and automatically form a long motion texture endlessly.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.