8 citations · 15 across the 23 of their papers we have counts for
14 papers · 1 filter
Generative Inbetweening through Frame-wise Conditions-Driven Video Generation
Tianyi Zhu, Dongwei Ren, Qilong Wang +2
Generative inbetweening aims to generate intermediate frame sequences by utilizing two key frames as input. Although remarkable progress has been made in video generation models, g…
Class Balance Matters to Active Class-Incremental Learning
Zitong Huang, Ze Chen, Yuanze Li +6
Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may…
Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention
Hannan Lu, Xiaohe Wu, Shudong Wang +5
Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Exist…
Combining Generative and Geometry Priors for Wide-Angle Portrait Correction
Lan Yao, Chaofeng Chen, Xiaoming Li +2
Wide-angle lens distortion in portrait photography presents a significant challenge for capturing photo-realistic and aesthetically pleasing images. Such distortions are especially…
VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models
Kailai Feng, Yabo Zhang, Haodong Yu +4
Artistic typography is a technique to visualize the meaning of input character in an imaginable and readable manner. With powerful text-to-image diffusion models, existing methods…
Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs
Dongwei Ren, Xinya Shu, Yu Li +3
For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map…
SelfDRSC++: Self-Supervised Dual Reversed Rolling Shutter Correction via Video Interpolation
Wei Shang, Dongwei Ren, Wanying Zhang +3
Modern consumer cameras often use rolling shutter, capturing scenes row-by-row and causing distortion in dynamic scenes. Existing correction methods rely on supervised learning wit…
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Mingxiang Liao, Hannan Lu, Xinyu Zhang +6
Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols…
Diffusion Models in Low-Level Vision: A Survey
Chunming He, Yuqi Shen, Chengyu Fang +6
Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterize…
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
Xin Li, Kun Yuan, Yajing Pei +65
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected da…
MC: Multi-concept Guidance for Customized Multi-concept Generation
Jiaxiu Jiang, Yabo Zhang, Kailai Feng +5
Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extende…
ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model
Binghui Chen, Wenyu Li, Yifeng Geng +2
With the development of the large-scale diffusion model, Artificial Intelligence Generated Content (AIGC) techniques are popular recently. However, how to truly make it serve our d…
A self-supervised CNN for image watermark removal
Chunwei Tian, Menghua Zheng, Tiancai Jiao +3
Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real…
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Yabo Zhang, Yuxiang Wei, Xianhui Lin +5
Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V)…