38 citations · 96 across the 15 of their papers we have counts for
15 papers
Can Large Pretrained Depth Estimation Models Help With Image Dehazing?
Hongfei Zhang, Kun Zhou, Ruizheng Wu +1
Image dehazing remains a challenging problem due to the spatially varying nature of haze in real-world scenes. While existing methods have demonstrated the promise of large-scale p…
Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement
Kun Zhou, Xinyu Lin, Wenbo Li +5
Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illuminatio…
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm
Kun Zhou, Wenbo Li, Nianjuan Jiang +2
Neural radiance fields (NeRF) have shown great success in novel view synthesis. However, recovering high-quality details from real-world scenes is still challenging for the existin…
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
Kun Zhou, Wenbo Li, Yi Wang +4
Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging…
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
Wenbo Li, Xin Yu, Kun Zhou +3
Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative probabilistic…
Mutual Guidance and Residual Integration for Image Enhancement
Kun Zhou, KenKun Liu, Wenbo Li +2
Previous studies show the necessity of global and local adjustment for image enhancement. However, existing convolutional neural networks (CNNs) and transformer-based models face g…
Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation
Kun Zhou, Wenbo Li, Xiaoguang Han +1
For video frame interpolation (VFI), existing deep-learning-based approaches strongly rely on the ground-truth (GT) intermediate frames, which sometimes ignore the non-unique natur…
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Wenbo Li, Zhe Lin, Kun Zhou +3
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attentio…
NLP Research and Resources at DaSciM, Ecole Polytechnique
Hadi Abdine, Yanzhu Guo, Moussa Kamal Eddine +5
DaSciM (Data Science and Mining) part of LIX at Ecole Polytechnique, established in 2013 and since then producing research results in the area of large scale data analysis via meth…
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Wenbo Li, Kun Zhou, Lu Qi +3
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed i…
Best-Buddy GANs for Highly Detailed Image Super-Resolution
Wenbo Li, Kun Zhou, Lu Qi +4
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input. Recently, generative adversarial…
HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation
Kun Zhou, Xiaoguang Han, Nianjuan Jiang +2
Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing a…
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
Kun Zhou, Xiaoguang Han, Nianjuan Jiang +2
Estimating 3D human pose from a single image is a challenging task. This work attempts to address the uncertainty of lifting the detected 2D joints to the 3D space by introducing a…
Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
Kun Zhou, Jinmiao Cai, Yao Li +5
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image. Specifically, a two-phase approach is developed. We firstly utilize a…
FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Yulong Shi, Xiaoguang Han, Nianjuan Jiang +3
Although significant advances have been made in the area of human poses estimation from images using deep Convolutional Neural Network (ConvNet), it remains a big challenge to perf…