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
- Christopher A. MetzlerSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works22 from public data
- PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration320
It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.
- Blueprint Separable Residual Network for Efficient Image Super-Resolution272
This paper proposes Blueprint Separable Residual Network (BSRN), a model containing two efficient designs, one of which is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation.
- 102
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- NTIRE 2022 Challenge on Perceptual Image Quality Assessment84
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022 to address the emerging challenge of IQA by perceptual image processing algorithms.
- NTIRE 2021 Challenge on Perceptual Image Quality Assessment55
The NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021, achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
- 46
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation28
This work overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI, and shows that this method outperforms existing methods and generalizes across cameras far better than existing approaches.
- 27
- 23
- Toward Interactive Modulation for Photo-Realistic Image Restoration22
A Controllable Unet Generative Adversarial Network (CUGAN) to generate high-frequency textures in the modulation tasks to achieve excellent performance on image restoration modulation tasks.
- CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras14
Tests establish theoretical limits (Cramér Rao bounds) on 3D point localization and tracking with PSF-engineered event cameras and designs are designed to overcome the non-convexity of the design problem.
- Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation12
This work introduces Flash-Split, a robust framework for separating transmitted and reflected light using a single (potentially misaligned) pair of flash/no-flash images that significantly outperforms existing methods in a low-dimensional latent space.
- Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats8
The key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods allow one to perform flash/no-flash reflection separation using unpaired measurements -- this relaxation dramatically simplifies image acquisition over conventional paired flash/no-flash reflection separation methods.
- Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations7
Inspired by the observation that atmospheric turbulence induces high-frequency temporal variations, ConVRT is proposed, a novel framework for consistent video restoration through turbulence that effectively mitigates turbulence-induced temporal frequency variations and promotes temporal consistency.
- Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models5
Despite training only on synthetic data built on real-world identities, Shadow Director generalizes ef-fectively to generated portraits with diverse styles, making it a more accessible and resource-friendly solution.
- TimeRewind: Rewinding Time with Image-and-Events Video Diffusion5
This paper addresses the novel challenge of ``rewinding'' time from a single captured image to recover the fleeting moments missed just before the shutter button is pressed, by leveraging the emerging technology of neuromorphic event cameras and integrating this data with advanced image-to-video diffusion models.
- 4
- Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion1
This work proposes Real2SAM2Real, a framework that leverages 3D lifting models to extract an explicitly editable 3D cache, serving as a robust geometric scaffold for the VDM, and designs a Soft Spatial-Aligned Injection mechanism alongside a minimally invasive fine-tuning strategy tailored for VDMs.
- –
- ConVRT: Consistent Video Restoration Through Turbulence with Test-time Optimization of Neural Video Representations–
This work introduces a self-supervised method, Consistent Video Restoration through Turbulence (ConVRT), a test-time optimization method featuring a neural video representation designed to enhance temporal consistency in restoration, and develops a principled selection strategy of text prompts, based on their statistical correlation with a perceptual metric.
- –
Publication data from OpenAlex; 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.