Search Results for author:
Found 125 papers, 80 papers with code
CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning
While separate adapters are proven to mitigate forgetting and fit unique requirements, naively applying them hinders the intrinsic connection between spatial and temporal information increments, affecting the efficiency of representing newly learned class information.
Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation
To further enhance fusion, we propose a transformer-based module that complements sparse event motion features with spatially rich frame information and enhances global information propagation.
ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation
However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event data.
Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?
Cross-modal contrastive distillation has recently been explored for learning effective 3D representations.
Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning
In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels.
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities.
Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer
Current methods for lossy point cloud attribute compression (PCAC) generally focus on reconstructing the original point clouds with minimal error.
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.
Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation
However, the spatial distribution of the HSI is always irregular, while the previous tensor low-rank representation methods can only be applied to the regular data cubes, which limits the performance.
Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds
In this paper, we propose the scaled-squared distance function (S$^{2}$DF), a novel implicit surface representation for modeling arbitrary surface types.
E-Motion: Future Motion Simulation via Event Sequence Diffusion
Inspired by that, we propose to integrate the strong learning capacity of the video diffusion model with the rich motion information of an event camera as a motion simulation framework.
VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking
In this paper, we propose VOVTrack, a novel method that integrates object states relevant to MOT and video-centric training to address this challenge from a video object tracking standpoint.
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e. g., low-quality images or a Gaussian distribution.
Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method
By leveraging both explicit and implicit depth cues present in 4-D LF images, we propose a progressive, mutually reinforcing framework for underwater 4-D LF image enhancement and depth estimation.
OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking
We study a novel yet practical problem of open-corpus multi-object tracking (OCMOT), which extends the MOT into localizing, associating, and recognizing generic-category objects of both seen (base) and unseen (novel) classes, but without the category text list as prompt.
Self-supervised 3D Point Cloud Completion via Multi-view Adversarial Learning
Additionally, we render the reconstructed complete shape into multi-view depth maps and design an adversarial learning module to learn the geometry of the target shape from category-specific single-view depth images.
Boosting 3D Object Detection with Semantic-Aware Multi-Branch Framework
In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information.
Learning Unsigned Distance Fields from Local Shape Functions for 3D Surface Reconstruction
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries.
MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos
In this paper, we propose MoDGS, a new pipeline to render novel views of dy namic scenes from a casually captured monocular video.
SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid Registration
Existing optimization-based methods for non-rigid registration typically minimize an alignment error metric based on the point-to-point or point-to-plane distance between corresponding point pairs on the source surface and target surface.
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit{without} the need for training.
Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
Contrastive image-to-LiDAR knowledge transfer, commonly used for learning 3D representations with synchronized images and point clouds, often faces a self-conflict dilemma.
Flatten Anything: Unsupervised Neural Surface Parameterization
Surface parameterization plays an essential role in numerous computer graphics and geometry processing applications.
RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering
We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images.
Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking
This paper tackles the problem of passive gaze estimation using both event and frame data.
DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction
Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape.
ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds
To the best of our knowledge, this work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and their optimization targets are not clustering-oriented.
Towards Calibrated Deep Clustering Network
Specifically, we propose a novel dual-head (calibration head and clustering head) deep clustering model that can effectively calibrate the estimated confidence and the actual accuracy.
Dynamic 3D Point Cloud Sequences as 2D Videos
The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences.
Unsupervised Learning of High-resolution Light Field Imaging via Beam Splitter-based Hybrid Lenses
In this paper, we design a beam splitter-based hybrid light field imaging prototype to record 4D light field image and high-resolution 2D image simultaneously, and make a hybrid light field dataset.
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration
First, we propose the learnable transformation alignment to bridge the domain gap between image and point cloud data, converting features into a unified representation space for effective comparison and matching.
3D Shape Completion on Unseen Categories:A Weakly-supervised Approach
Specifically, we construct a prior bank consisting of representative shapes from the seen categories.
Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields
We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence.
On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding
Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate.
Hybrid Pooling and Convolutional Network for Improving Accuracy and Training Convergence Speed in Object Detection
This paper introduces HPC-Net, a high-precision and rapidly convergent object detection network.
Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens
One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery.
Segment Any Events via Weighted Adaptation of Pivotal Tokens
One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery.
Ranked #1 on
Event-based Object Segmentation
on DSEC-SEG
Cross-BERT for Point Cloud Pretraining
By performing cross-modal interaction, Cross-BERT can smoothly reconstruct the masked tokens during pretraining, leading to notable performance enhancements for downstream tasks.
Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images
The latest trends in the research field of single-view human reconstruction devote to learning deep implicit functions constrained by explicit body shape priors.
Global Structure-Aware Diffusion Process for Low-Light Image Enhancement
To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.
Ranked #3 on
Low-Light Image Enhancement
on LOL
Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions.
Downstream-agnostic Adversarial Examples
AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder.
Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers
This paper addresses the problem of cross-modal object tracking from RGB videos and event data.
Ranked #1 on
Object Tracking
on COESOT
Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising
The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks.
Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric
By associating each reference point with two given point clouds through computing its directional distances to them, the difference in directional distances of an identical reference point characterizes the geometric difference between a typical local region of the two point clouds.
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
To bridge this gap, this paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions.
Decoupling Dynamic Monocular Videos for Dynamic View Synthesis
Such a fine-grained motion formulation can alleviate the learning difficulty for the network, thus enabling it to produce not only novel views with higher quality but also more accurate scene flows and depth than existing methods requiring extra supervision.
GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute
To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently.
Unleash the Potential of Image Branch for Cross-modal 3D Object Detection
To achieve reliable and precise scene understanding, autonomous vehicles typically incorporate multiple sensing modalities to capitalize on their complementary attributes.
PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation
The past few years have witnessed the great success and prevalence of self-supervised representation learning within the language and 2D vision communities.
A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks
Specifically, we extend three distinct adversarial attacks to the 3D object detection task, benchmarking the robustness of state-of-the-art LiDAR-based 3D object detectors against attacks on the KITTI and Waymo datasets.
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels.
Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion
The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin.
GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
We present a learning-based method, namely GeoUDF, to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface.
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.
EGRC-Net: Embedding-induced Graph Refinement Clustering Network
To begin, we leverage both semantic and topological information by employing a vanilla auto-encoder and a graph convolution network, respectively, to learn a latent feature representation.
Learning A Locally Unified 3D Point Cloud for View Synthesis
To tackle this challenging problem, we propose a new deep learning-based view synthesis paradigm that learns a locally unified 3D point cloud from source views.
Ecsnet: Spatio-temporal feature learning for event camera
To fully exploit their inherent sparsity with reconciling the spatio-temporal information, we introduce a compact event representation, namely 2D-1T event cloud sequence (2D-1T ECS).
Ranked #1 on
Gesture Generation
on DVS128 Gesture
CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence
Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i. e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence.
Ranked #1 on
Image to Point Cloud Registration
on KITTI
Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising
This paper tackles the challenging problem of hyperspectral (HS) image denoising.
PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition
In this paper, we explore the possibility of boosting deep 3D point cloud encoders by transferring visual knowledge extracted from deep 2D image encoders under a standard teacher-student distillation workflow.
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors to build probabilistic detectors and supervise the learning of the localization uncertainty.
Ranked #2 on
3D Object Detection
on KITTI Cars Easy
Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network
Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M), and Remain-Centers-to-Mask (RC2M) algorithms.
Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing lightweight PDE-Net, in which high-resolution (HR) HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR-HS images via probability-inspired HS embedding.
Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation
In this letter, we propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discriminative affinity matrix.
Light Field Depth Estimation via Stitched Epipolar Plane Images
This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions.
WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation
We propose WarpingGAN, an effective and efficient 3D point cloud generation network.
IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation.
PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
Content-aware Warping for View Synthesis
To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network.
Deep Attention-guided Graph Clustering with Dual Self-supervision
Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation.
Adaptive Attribute and Structure Subspace Clustering Network
In this paper, we propose a novel adaptive attribute and structure subspace clustering network (AASSC-Net) to simultaneously consider the attribute and structure information in an adaptive graph fusion manner.
Superpixel-guided Discriminative Low-rank Representation of Hyperspectral Images for Classification
Specifically, by utilizing the local spatial information and incorporating the predictions from a typical classifier, the first module segments pixels of an input HSI (or its restoration generated by the second module) into superpixels.
Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines
In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation.
Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild
Specifically, on the basis of the intrinsic imaging degradation model of RGB images from HS images, we progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective unsupervised camera spectral response function estimation.
Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images
Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.
Attention-driven Graph Clustering Network
The combination of the traditional convolutional network (i. e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature.
PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows
Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets.
Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.
Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields
Experimental results on synthetic data show that our method can significantly shrink the performance gap between the previous unsupervised method and supervised ones, and produce depth maps with comparable accuracy to traditional methods with obviously reduced computational cost.
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding
As a result, our network can effectively improve the visual quality of underwater images by exploiting multiple color spaces embedding and the advantages of both physical model-based and learning-based methods.
Ranked #3 on
Underwater Image Restoration
on LSUI
(using extra training data)
Self-supervised Symmetric Nonnegative Matrix Factorization
Inspired by ensemble clustering that aims to seek a better clustering result from a set of clustering results, we propose self-supervised SNMF (S$^3$NMF), which is capable of boosting clustering performance progressively by taking advantage of the sensitivity to initialization characteristic of SNMF, without relying on any additional information.
Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses
Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
Ranked #6 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
Clustering Ensemble Meets Low-rank Tensor Approximation
The existing clustering ensemble methods generally construct a co-association matrix, which indicates the pairwise similarity between samples, as the weighted linear combination of the connective matrices from different base clusterings, and the resulting co-association matrix is then adopted as the input of an off-the-shelf clustering algorithm, e. g., spectral clustering.
Maximum Entropy Subspace Clustering Network
Furthermore, we design a novel framework to explicitly decouple the auto-encoder module and the self-expressiveness module.
ParaNet: Deep Regular Representation for 3D Point Clouds
Although convolutional neural networks have achieved remarkable success in analyzing 2D images/videos, it is still non-trivial to apply the well-developed 2D techniques in regular domains to the irregular 3D point cloud data.
Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression
In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate.
Deep Magnification-Flexible Upsampling over 3D Point Clouds
In addition, we propose a simple yet effective training strategy to drive such a flexible ability.
Recurrent Multi-view Alignment Network for Unsupervised Surface Registration
Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data.
CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection
In the first stage, we propose a group-attentional semantic aggregation module that models inter-image relationships to generate the group-wise semantic representations.
Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution
To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation.
Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display
The impact of distorted geometry and texture attributes is further discussed in this paper.
A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i. e., objects are labeled with points) to estimate both the center points and sizes of crowded objects.
Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms.
Image and Video Processing
Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning
Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension.
Hyperspectral Image Super-Resolution
Hyperspectral Unmixing
+1
MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling
This paper explores the problem of task-oriented downsampling over 3D point clouds, which aims to downsample a point cloud while maintaining the performance of subsequent applications applied to the downsampled sparse points as much as possible.
Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation
On the basis of the novel tensor low-rank norm, we formulate MVSC as a convex low-rank tensor recovery problem, which is then efficiently solved with an augmented Lagrange multiplier based method iteratively.
When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks
However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.
Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension.
Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
In addition, our method preserves the light field parallax structure better.
PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling
Matrix $\mathbf T$ approximates the augmented Jacobian matrix of a local parameterization and builds a one-to-one correspondence between the 2D parametric domain and the 3D tangent plane so that we can lift the adaptively distributed 2D samples (which are also learned from data) to 3D space.
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
Ranked #1 on
Color Constancy
on INTEL-TUT2
Non-Cooperative Game Theory Based Rate Adaptation for Dynamic Video Streaming over HTTP
The proposed algorithm is proxy-free.
An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP
Specifically, the proposed framework is composed of two modules, i. e., the method pool and method controller.
Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos
That is, our method preserves both the quality and the smoothness of tiles in FoV, thus providing the best QoE for users.
A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
Hyperspectral Image Classification via Sparse Representation With Incremental Dictionaries
In this letter, we propose a new sparse representation (SR)-based method for hyperspectral image (HSI) classification, namely SR with incremental dictionaries (SRID).
Convolutional Neural Networks with Dynamic Regularization
That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures.
Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware Fusion
Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF.
Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses
To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input.
Single Image based Head Pose Estimation with Spherical Parameterization and 3D Morphing
Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/ manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i. e., scale factor and translation parameters).
Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI.
Clustering-aware Graph Construction: A Joint Learning Perspective
Graph-based clustering methods have demonstrated the effectiveness in various applications.
Stratified Labeling for Surface Consistent Parallax Correction and Occlusion Completion
A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities.
An Underwater Image Enhancement Benchmark Dataset and Beyond
In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images.
Ranked #6 on
Underwater Image Restoration
on LSUI
(using extra training data)
Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues
Specifically, our end-to-end model first synthesizes a set of intermediate novel sub-aperture images (SAIs) by exploring the coarse characteristics of the sparsely-sampled LF input with spatial-angular alternating convolutions.
Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays.
Robust Video Content Alignment and Compensation for Clear Vision Through the Rain
Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes.
Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
Visual inspection shows that much cleaner rain removal is achieved especially for highly dynamic scenes with heavy and opaque rainfall from a fast moving camera.
Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions
Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions.
Light Field Compression with Disparity Guided Sparse Coding based on Structural Key Views
Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world.
