Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Thomas S. HuangSuggested from co-authorship
- Bertram Emil ShiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works62 from public data
- 608
- 545
- Horizontal Pyramid Matching for Person Re-Identification512
A simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be still identified even even some key parts are missing.
- 413
- Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory185
The ability of machine learning models to improve the authors' ICU decision making accuracy is highlighted, and is a real-world example of precision medicine in hospitals.
- When AWGN-Based Denoiser Meets Real Noises176
This paper proposes a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN, and investigates Pixel-shuffle Down-sampling strategy to adapt the trained model to real noises.
- Pyramid Attention Network for Image Restoration142
A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels.
- UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics115
UniReal, a unified framework designed to address various image generation and editing tasks, treats varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc.
- Towards Layer-wise Image Vectorization114
This work proposes Layer-wise Image Vectorization, namely LIVE, to convert raster images to SVGs and simultaneously maintain its image topology, and demonstrates that LIVE presents more plausible vectorized forms than prior works and can be generalized to new images.
- 110
- NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results106
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results, based on the SIDD benchmark.
- TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations98
This paper proposes TransFill, a multi-homography transformed fusion method to fill the hole by referring to another source image that shares scene contents with the target image, and generalizes to user-provided image pairs.
- Image Restoration for Under-Display Camera92
This paper designs a Monitor-Camera Imaging System (MCIS) for easier real pair data acquisition, and a model-based data synthesizing pipeline to generate Point Spread Function (PSF) and UDC data only from display pattern and camera measurements, and resolves the complicated degradation using deconvolution-based pipeline and learning-based methods.
- Image as Set of Points83
Context clusters aim at providing a new perspective on image and visual representation, which may enjoy broad applications in different domains and exhibit profound insights, and achieve comparable or even better results than Convolutional Networks or ViTs on several benchmarks.
- Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand83
A novel inpainting network combining the advantages of the two designs achieves a remarkable visual quality to match state-of-the-art performance in both structure generation and repeating texture synthesis using a single network.
- Photorealistic facial expression synthesis by the conditional difference adversarial autoencoder82
The experimental results demonstrate that the CDAAE can preserve identity information when generating facial expression for unseen subjects more faithfully than previous approaches, especially advantageous when training with small databases.
- Survey of Face Detection on Low-Quality Images80
The results demonstrate that both hand-crafted and deep-learning based face detectors are not robust enough for low-quality images, and inspires researchers to produce more robust design for face detection in the wild.
- Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation78
A Bayer pattern unification (BayerUnify) method to unify different Bayer patterns is proposed to fully utilize a heterogeneous dataset to train a single denoising model instead of training one model for each pattern.
- Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels76
This paper proposes a Study Group Learning (SGL) scheme to improve the robustness of the model trained on noisy labels, and shows that a learned enhancement map provides better visualization than conventional methods as an auxiliary tool for clinicians.
- 65
- FLNet: Landmark Driven Fetching and Learning Network for Faithful Talking Facial Animation Synthesis65
A landmark driven two-stream network to generate faithful talking facial animation, in which more facial details are created, preserved and transferred from multiple source images instead of a single one.
- High-Resolution Deep Image Matting64
The proposed HDMatt approach runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches.
- Perceptual Artifacts Localization for Image Synthesis Tasks54
This study introduces a novel dataset comprising 10, 168 generated images, each annotated with per-pixel perceptual artifact labels across ten synthesis tasks, and proposes an innovative zoom-in inpainting pipeline that seamlessly rectifies perceptual artifacts in the generated images.
- MIMAMO Net: Integrating Micro- and Macro-Motion for Video Emotion Recognition53
This paper proposes to combine micro- and macro-motion features to improve video emotion recognition with a two-stream recurrent network, named MIMAMO (Micro-Macro-Motion) Net, achieves state of the art performance on two video emotion datasets, the OMG emotion dataset and the Aff-Wild dataset.
- GeoNet: Deep Geodesic Networks for Point Cloud Analysis48
This work introduces GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds, and proposes fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis.
- 40
- 40
- UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results38
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
- Baking Gaussian Splatting Into Diffusion Denoiser for Fast and Scalable Single-Stage Image-to-3D Generation and Reconstruction36
A novel single-stage 3D diffusion model, DiffusionGS, for object generation and scene reconstruction from a single view, which directly outputs 3D Gaussian point clouds at each timestep to enforce view consistency and allow the model to generate robustly given prompt views of any directions, beyond object-centric inputs.
- 28
- TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting19
TurboFill is introduced, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpainting.
- 18
- Automatic High Resolution Wire Segmentation and Removal14
This paper proposes a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given the authors' predicted segmentation masks.
- GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding11
This work proposes a principled approach that does not make heuristic assumptions about the planarity of the scene and achieves state-of-the-art performance on both RealEstate10K and MannequinChallenge dataset with large baselines, complex geometry and extreme camera motions.
- 11
- 9
- SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Network8
An interactive distractor selection method that is optimized to achieve the task with just a single click is proposed, which surpasses the precision and recall achieved by the traditional method of running panoptic segmentation and then selecting the segments containing the clicks.
- 8
- 8
- 7
- Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise6
This paper trained a deep network integrating noise estimating and denoiser with mixed Gaussian (AWGN) and Random Value Impulse Noise (RVIN) to adapt the model to realistic noises, and investigated multi-channel, multi-scale and super-resolution approaches.
- 4
- 4
- 2
- Structure-Guided Image Completion With Image-Level and Object-Level Semantic Discriminators2
This work proposes a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects and achieves state-of-the-art results on the standard inpainting task.
- 2
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.