KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation Guanwen Feng 1,2,3 , Siyu Jin 1,2,3 , Zhihao Qian 1,2,3 , Yunan Li 1,2,3 , Qiguang Miao 1,2,3

Introduced by Georgopoulos et al. in Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study KANFace consists of 40K still images and 44K sequences (14.5M video frames in total) captured in unconstrained, real-world conditions from 1,045 subjects.

[ICASSP 2025] KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation Guanwen Feng, Siyu Jin, Zhihao Qian, Yunan Li, Qiguang Miao Project / We propose a novel 3D Gaussian-based talking head generation method.

2024年9月27日 · In this work, we introduce the first approach to exploit Kolmogorov-Arnold Network (KAN) for conducting embedding-to-face attacks against state-of-the-art (SOTA) FR and PPFR systems. Face embedding mapping (FEM) models are proposed to learn the distribution mapping relation between the embeddings from the initial domain and target domain.

2024年9月9日 · In this paper, we propose the KFusion of Dual-Domain model, a robust model that generates landmarks from audio. We separate the audio into two distinct domains to learn emotional information and facial context, then use a fusion mechanism based on the KAN model. Our model demonstrates high efficiency compared to recent models.

2024年5月12日 · Kolmogorov-Arnold Networks（简称 KAN）是一种新型神经网络架构，灵感来源于 Kolmogorov-Arnold 表示定理。 与传统使用 固定激活函数 的神经网络不同，KAN 在网络的 边缘 采用 可学习的激活函数。 这种设计使得 KAN 中每个权重参数都可以被一个单变量函数替换，这些函数通常以 样条 函数形式参数化，从而提供了极高的灵活性，并能够用更少的参数来模拟复杂的函数，增强了模型的可解释性。 Kolmogorov-Arnold Networks (KAN) 的架构围绕一个创新 …

30 open source face images and annotations in multiple formats for training computer vision models. Kan Face (v1, face_v1), created by TNI Project

In this paper, we introduce Wav-KAN, an innovative neural network architecture that leverages the Wavelet Kolmogorov-Arnold Networks (Wav-KAN) framework to enhance interpretability and performance. Traditional multilayer perceptrons (MLPs) and even recent advancements like Spl-KAN face challenges such as:

2024年9月5日 · The recently proposed Kolmogorov-Arnold networks (KANs) feature spline-based convolutional layers and learnable activation functions, which can effectively capture nonlinear dependencies. In this paper, we design a KAN-Block based on KANs and innovatively apply it to low-light image enhancement.

2024年8月21日 · KAN卷积（KAN Convolutions）是一种特殊的卷积操作，它在每个边缘上应用一个可学习的非线性函数 通信：工信部再 发文 ！ 从3点边际变化，看工业互联网发展提速.pdf