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
- Luc Van GoolSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works45 from public data
- Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement884
A simple yet principled One-stage Retinex-based Framework (ORF), designed an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions, and obtains the algorithm, Retinexformer.
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction423
A novel framework, Mask-guided Spectral-wise Transformer (MST), that treats each spectral feature as a token and calculates self-attention along the spectral dimension and significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs.
- MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction364
This work proposes a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction that significantly outperforms other state-of-the-art methods.
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging250
A high-resolution dual-domain learning network (HDNet) for HSI reconstruction with HR pixel-level attention and frequency-level refinement that achieves SOTA performance on simulated and real HSI datasets.
- Learning Delicate Local Representations for Multi-person Pose Estimation242
This paper proposes 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.
- 189
- 149
- Structure-Aware Sparse-View X-Ray 3D Reconstruction122
This paper designs a Line Segment-based Transformer (Lineformer) as the backbone of SAX-NeRF, a framework for sparse-view X-ray 3D reconstruction and presents a Masked Local-Global ray sampling strategy to extract contextual and geometric information in 2D projection.
- RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark86
A novel Transformer-based Generative Adversarial Network (RFormer) is proposed to restore the real degradation of clinical fundus images and significantly outperforms the state-of-the-art (SOTA) methods.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training81
Qualitative validation shows that noise generated by PNGAN is highly similar to real noise in terms of intensity and distribution, and an efficient architecture Simple Multi-scale Network (SMNet) as the generator is presented.
- Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset47
A scalable annotation pipeline is developed that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.1K text-motion pairs, a large-scale multimodal 3D expressive whole-body human motion dataset.
- 41
- Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration30
This work proposes an unsupervised flow-aligned sequence-to-sequence model (S2SVR), which shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement.
- 30
- Exosomes in neurodegenerative diseases: Therapeutic potential and modification methods27
The findings indicate that exosomes can efficiently cross the blood–brain barrier to facilitate drug delivery and can also serve as early diagnostic markers for neurodegenerative diseases.
- 22
- 20
- Repair effect of photobiomodulation combined with human umbilical cord mesenchymal stem cells on rats with acute lung injury12
Photobiomodulation (PBM) effciently promotes cell proliferation, migration and homing, which presents a promising strategy for overcoming above limitations and further strengthens the therapeutic effect of hUCMSCs and depicted a hopeful therapy in ALI treatment.
- VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment11
VideoLifter is introduced, a novel video-to-3D pipeline that leverages a local-to-global strategy on a fragment basis, achieving both extreme efficiency and SOTA quality and significantly accelerates the reconstruction process.
- 11
- Efficient Human Pose Estimation by Learning Deeply Aggregated Representations11
This paper proposes an efficient human pose estimation network (DANet) by learning deeply aggregated representations and proposes an orthogonal attention block (OAB) and a second-order fusion unit (SFU) that could achieve comparable or even better accuracy with much smaller model complexity.
- $\mathbf{X}^{\mathbf{2}}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-Time Tomographic Reconstruction9
This work proposes X2 Gaussian, a novel framework that enables continuoustime 4D-CT reconstruction by integrating dynamic radiative Gaussian splatting with self-supervised respiratory motion learning and introduces a physiology-driven periodic consistency loss that learns patient-specific breathing cycles directly from projections via differentiable optimization.
- X-LRM: X-Ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second8
An X-ray Large Reconstruction Model for extremely sparse-view (<10 views) CT reconstruction that outperforms the state-of-the-art method by 1.5 times, achieves faster speed with better flexibility and the evaluation of lung segmentation tasks also suggests the practical value of the approach.
- Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?8
CARE, a Completeness-Aware Reconstruction Enhancement framework that incorporates structural penalties during training to encourage anatomical preservation of significant structures, is introduced and can be seamlessly integrated into analytical, implicit, and generative methods.
- Multi-Scale Selective Feedback Network with Dual Loss for Real Image Denoising8
A multi-scale selective feedback network (MSFN) with the dual loss that allows shallow layers to access valuable contextual information from the following deep layers selectively between two adjacent time steps and shows better adaptability on real-world images than the existing methods.
- 5
- Photobiomodulation Combined With Human Umbilical Cord Mesenchymal Stem Cells Modulates the Polarization of Microglia4
The results show that PBM‐pretreated hUCMSCs promoted M2 polarization and improved cognitive function in mice by downregulating the Notch signaling pathway, suggesting a promising new approach for treating neurodegenerative diseases.
- 4
- 2
- 2
- 1
- Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction1
FMU, a deep unfolding framework that couples a measurement-conditioned flow-matching prior with a sensing-model-guided measurement update, is proposed and quantitative simulated-CASSI results and qualitative reconstructions of real CASSI measurements are reported.
- 1
- EG^2N: enhanced gradient guiding network for single MR image super-resolution1
An enhanced gradient guiding network (EG2N) is proposed to alleviate problems of superresolution methods with usage of deep learning, where some low-level structural information tends to gradually disappear as the network deepens, resulting in excessive smoothness in high-frequency regions.
- –
- –
- –
- –
- Integrated control strategy for intelligent electric vehicle path tracking with time-varying feature considerations–
This paper proposes a control strategy that integrates an adaptive linear quadratic regulator (IALQR) with a radial basis function neural network (RBFNN)-based adaptive feedforward control, effectively mitigating the impact of time-varying parameter variations.
- Principles and Key Technologies of Magnetic Particle Imaging System: A Comprehensive Review–
A systematic review of the principles and key technologies of the MPI system through literature searches in databases including PubMed, Web of Science, and Google Scholar is conducted, aiming to deepen the understanding of device applications.
- –
- Wireless bluetooth noise-canceling headphones exploring the design principles and different categories of products–
The noise-cancellation technology in commonly-seen Bluetooth headphones in the market is observed and the future outlook is provided to display the current limitation of Bluetooth headphones, which mainly demonstrates the active noise-cancellation technology.
- ITportrait: Image-Text Coupled 3D Portrait Domain Adaptation–
An Image-Text multi-modal framework, namely Image and Text portrait (ITportrait), for 3D portrait domain adaptation, which relies on a two-stage alternating training strategy and achieves state-of-the-art (SOTA) results.
- 3D Face Arbitrary Style Transfer–
Face-guided Dual Style Transfer can be applied in many downstream tasks, including region-controllable style transfer, high-fidelity face texture reconstruction, large-pose face reconstruction, and artistic face reconstruction.
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.