Search Results for author:
Found 6 papers, 5 papers with code
Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement
In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical perspective, emphasizing the learning of distributions rather than individual pixel values.
BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding
Current models are limited in their ability to render a specific set of bokeh effects, primarily transformations from sharp to blur.
Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
Sliding Window Recurrent Network for Efficient Video Super-Resolution
Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with more details.
Kernel-aware Burst Blind Super-Resolution
In this paper, we address the problem of reconstructing HR images from raw burst sequences acquired from a modern handheld device.
Ranked #5 on
Burst Image Super-Resolution
on BurstSR
