paper-with-me

홈 › Papers

CPNet: Exploiting CLIP-based Attention Condenser and Probability Map Guidance for High-fidelity Talking Face Generation

2023-05-23 · Jingning Xu, Benlai Tang, Mingjie Wang, Minghao Li, Meirong Ma

Recently, talking face generation has drawn ever-increasing attention from the research community in computer vision due to its arduous challenges and widespread application scenarios, e.g. movie animation and virtual anchor. Although persevering efforts have been undertaken to enhance the fidelity and lip-sync quality of generated talking face videos, there is still large room for further improvements of synthesis quality and efficiency. Actually, these attempts somewhat ignore the explorations of fine-granularity feature extraction/integration and the consistency between probability distributions of landmarks, thereby recurring the issues of local details blurring and degraded fidelity. To mitigate these dilemmas, in this paper, a novel CLIP-based Attention and Probability Map Guided Network (CPNet) is delicately designed for inferring high-fidelity talking face videos. Specifically, considering the demands of fine-grained feature recalibration, a clip-based attention condenser is exploited to transfer knowledge with rich semantic priors from the prevailing CLIP model. Moreover, to guarantee the consistency in probability space and suppress the landmark ambiguity, we creatively propose the density map of facial landmark as auxiliary supervisory signal to guide the landmark distribution learning of generated frame. Extensive experiments on the widely-used benchmark dataset demonstrate the superiority of our CPNet against state of the arts in terms of image and lip-sync quality. In addition, a cohort of studies are also conducted to ablate the impacts of the individual pivotal components.

📄 PDF Abstract BibTeX arXiv:2305.13962

Code (0)

등록된 구현이 없습니다.

Tasks

Face GenerationTalking Face Generation

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers

2022-08-15 · Alexander Wong, Mohammad Javad Shafiee, Saad Abbasi, Saeejith Nair 외

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attentio…

Efficient Neural Network

TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices

2020-08-10 · Alexander Wong, Mahmoud Famouri, Maya Pavlova, Siddharth Surana

Advances in deep learning have led to state-of-the-art performance across a multitude of speech recognition tasks. Nevertheless, the widespread deployment of deep neural networks for on-device speech recognition remains …

speech-recognitionSpeech Recognition

AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers

2020-09-30 · Alexander Wong, Mahmoud Famouri, Mohammad Javad Shafiee

While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications…

Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis

2023-06-16 · Andre Hryniowski, Alexander Wong

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune …

Condenser: a Pre-training Architecture for Dense Retrieval

2021-04-16 · EMNLP 2021 11 · Luyu Gao, Jamie Callan

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representat…

Language ModellingRetrievalText Retrieval