Search Results for author:
Found 53 papers, 26 papers with code
Fast and High Quality Highlight Removal from A Single Image
Specifically, this paper derives a normalized dichromatic model for the pixels with identical diffuse color: a unit circle equation of projection coefficients in two subspaces that are orthogonal to and parallel with the illumination, respectively.
A PID Controller Approach for Stochastic Optimization of Deep Networks
We first reveal the intrinsic connections between SGD-Momentum and PID based controller, then present the optimization algorithm which exploits the past, current, and change of gradients to update the network parameters.
CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
The Reference-based Super-resolution (RefSR) super-resolves a low-resolution (LR) image given an external high-resolution (HR) reference image, where the reference image and LR image share similar viewpoint but with significant resolution gap x8.
SPI-Optimizer: an integral-Separated PI Controller for Stochastic Optimization
Inspired by the conditional integration idea in classical control society, we propose SPI-Optimizer, an integral-Separated PI controller based optimizer WITHOUT introducing extra hyperparameter.
STAR: A Structure and Texture Aware Retinex Model
A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image.
Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier.
Non-negative Sparse and Collaborative Representation for Pattern Classification
In this paper, we propose a novel Non-negative Sparse and Collaborative Representation (NSCR) for pattern classification.
Learning Delicate Local Representations for Multi-Person Pose Estimation
To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.
Ranked #1 on
Keypoint Detection
on COCO test-challenge
Enabling the Network to Surf the Internet
Few-shot learning is challenging due to the limited data and labels.
Pseudo 3D Auto-Correlation Network for Real Image Denoising
The extraction of auto-correlation in images has shown great potential in deep learning networks, such as the self-attention mechanism in the channel domain and the self-similarity mechanism in the spatial domain.
Imaging dynamics beneath turbid media via parallelized single-photon detection
Noninvasive optical imaging through dynamic scattering media has numerous important biomedical applications but still remains a challenging task.
PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods.
Real-time Human-Centric Segmentation for Complex Video Scenes
To alleviate this problem, we propose a mechanism named Inner Center Sampling to improve the accuracy of instance segmentation.
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
The HSI representations are highly similar and correlated across the spectral dimension.
Ranked #2 on
Spectral Reconstruction
on ARAD-1K
Flow-Guided Sparse Transformer for Video Deblurring
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring.
Ranked #1 on
Deblurring
on DVD
r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation
In this paper, we aim to evaluate and enhance the robustness of G2P models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Light field disparity estimation is an essential task in computer vision with various applications.
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features.
Ranked #5 on
Spectral Reconstruction
on Real HSI
Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i. e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement.
Ranked #2 on
Spectral Reconstruction
on Real HSI
Transient motion classification through turbid volumes via parallelized single-photon detection and deep contrastive embedding
We evaluate our setup by classifying different spatiotemporal-decorrelating patterns hidden beneath a 5mm tissue-like phantom made with rapidly decorrelating dynamic scattering media.
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
Additionally, for better noise fitting, we present an efficient architecture Simple Multi-scale Network (SMNet) as the generator.
Ranked #1 on
Noise Estimation
on SIDD
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI).
Ranked #1 on
Spectral Reconstruction
on ARAD-1K
Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential.
Ranked #2 on
Video Enhancement
on MFQE v2
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement.
Ranked #1 on
Spectral Reconstruction
on Real HSI
Delving into the Pre-training Paradigm of Monocular 3D Object Detection
(2) Combining depth estimation and 2D object detection is a promising M3OD pre-training baseline.
Multiple Instance Learning with Mixed Supervision in Gleason Grading
We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level.
Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition
For multi-head attention in Transformer ASR, it is not easy to model monotonic alignments in different heads.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation
Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited.
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention
Temporal action localization (TAL) aims to detect the boundary and identify the class of each action instance in a long untrimmed video.
Template-guided Hierarchical Feature Restoration for Anomaly Detection
Targeting for detecting anomalies of various sizes for complicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which introduces two key techniques, bottleneck compression and template-guided compensation, for anomaly-free feature restoration.
Ranked #11 on
Anomaly Detection
on MVTec LOCO AD
LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image
Gigapixel Whole Slide Images (WSIs) aided patient diagnosis and prognosis analysis are promising directions in computational pathology.
NeRF-MS: Neural Radiance Fields with Multi-Sequence
Neural radiance fields (NeRF) achieve impressive performance in novel view synthesis when trained on only single sequence data.
Iterative Few-shot Semantic Segmentation from Image Label Text
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images.
Ranked #40 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image
Moreover, we highlight AugDiff's higher-quality augmented feature over image augmentation and its superiority over self-supervised learning.
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
When enhancing low-light images, many deep learning algorithms are based on the Retinex theory.
Ranked #1 on
Low-Light Image Enhancement
on SDSD-outdoor
Low-light Image Deblurring and Enhancement
Low-Light Image Enhancement
+3
3D Face Arbitrary Style Transfer
To solve this problem, we propose a novel method, namely Face-guided Dual Style Transfer (FDST).
Calibrated Teacher for Sparsely Annotated Object Detection
Recent works on sparsely annotated object detection alleviate this problem by generating pseudo labels for the missing annotations.
One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
It is challenging to perform this task with a single network due to resolution issues, i. e., the face and hands are usually located in extremely small regions.
Ranked #3 on
3D Human Pose Estimation
on UBody
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks.
Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting
Detailed 3D reconstruction and photo-realistic relighting of digital humans are essential for various applications.
Binarized Spectral Compressive Imaging
Finally, our BiSRNet is derived by using the proposed techniques to binarize the base model.
Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset.
GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping
Besides, GroupLane with ResNet18 still surpasses PersFormer by 4. 9% F1 score, while the inference speed is nearly 7x faster and the FLOPs is only 13. 3% of it.
DT-NeRF: Decomposed Triplane-Hash Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
In this paper, we present the decomposed triplane-hash neural radiance fields (DT-NeRF), a framework that significantly improves the photorealistic rendering of talking faces and achieves state-of-the-art results on key evaluation datasets.
High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
One crucial aspect of 3D head avatar reconstruction lies in the details of facial expressions.
Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars
Neural radiance fields are capable of reconstructing high-quality drivable human avatars but are expensive to train and render.
Improving Medical Report Generation with Adapter Tuning and Knowledge Enhancement in Vision-Language Foundation Models
Medical report generation demands automatic creation of coherent and precise descriptions for medical images.
DPoser: Diffusion Model as Robust 3D Human Pose Prior
Our approach demonstrates considerable enhancements over common uniform scheduling used in image domains, boasting improvements of 5. 4%, 17. 2%, and 3. 8% across human mesh recovery, pose completion, and motion denoising, respectively.
LangSplat: 3D Language Gaussian Splatting
Humans live in a 3D world and commonly use natural language to interact with a 3D scene.
FFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information
To address this limitation, we propose a Feature-based Fast Cascade Alignment network (FFCA-Net) to fully leverage the side information on the decoder.
Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections
The photometric variation and transient occluders in those unconstrained images make it difficult to reconstruct the original scene accurately.
TexVocab: Texture Vocabulary-conditioned Human Avatars
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation.
