Zhihang Zhong,Yiming Zhang,Wei Wang et al.
Zhihang Zhong et al.
Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep $t$ ("time indexing"), which struggles to predict precise object movements. Given two images of a baseball, there are infinitely ma...
SSD: Making Face Forgery Clues Evident Again With Self-Steganographic Detection [0.03%]
SSD：自隐形检测使操纵痕迹重获证据效力
Ruiyang Xia,Dawei Zhou,Lin Yuan et al.
Ruiyang Xia et al.
The rapid development of generative AI techniques enables the synthesis of highly realistic facial images, posing significant challenges for the accurate detection of face forgeries. In contrast to solely elevating detector awareness, proac...
Evolving Markov Chains: Online Mode Discovery and Recognition from Data Streams [0.03%]
马尔可夫链的演变：从数据流中在线模式发现和识别
Kutalmls Coskun,Borahan Tumer,Bjarne C Hiller et al.
Kutalmls Coskun et al.
Markov chains are simple yet powerful mathematical structures to model temporally dependent processes. They generally assume stationary data, i.e., fixed transition probabilities between observations/states. However, live, real-world proces...
Qisen Wang,Yifan Zhao,Jia Li
Qisen Wang
The majority of standard diffusion models employ pixel-wise degradations while neglecting multi-scale characteristics of images. Recently, generalized diffusion models with Positive Semi-definite Degradations (PSD), such as heat dissipation...
Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks [0.03%]
通过坐标网络中的归一化来缓解谱偏差
Zhicheng Cai,Hao Zhu,Qiu Shen et al.
Zhicheng Cai et al.
Representing signals using coordinate networks dominates the area of inverse problems recently, and is widely applied in various scientific computing tasks. Still, there exists an issue of spectral bias in coordinate networks, limiting the ...
CLIP-Actor-X: Text-driven 4D Human Avatar Generation via Cross-modal Synthesis-through-Optimization [0.03%]
基于跨模态合成优化的文本驱动4D人脸生成方法
Kim Youwang,Taehyun Byun,Kim Ji-Yeon et al.
Kim Youwang et al.
We propose CLIP-Actor-X, a text-driven motion generation and neural mesh stylization system for 4D human avatar generation. CLIP-Actor-X generates a detailed 3D human mesh, motion animation, and texture to conform to a given text prompt inp...
Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning [0.03%]
基于编码器嵌入的图神经网络以改进节点学习
Shiyu Chen,Cencheng Shen,Youngser Park et al.
Shiyu Chen et al.
Graph neural networks (GNNs) have emerged as a powerful framework for a wide range of node-level graph learning tasks. However, their performance typically depends on random or minimally informed initial feature representations, where poor ...
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning [0.03%]
基于密集奖励差异学习的Few-Step扩散模型对齐
Ziyi Zhang,Li Shen,Sen Zhang et al.
Ziyi Zhang et al.
Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state s...
DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes [0.03%]
驱动高斯++：周围动态驾驶场景的现实重构与可编辑模拟研究
Yajiao Xiong,Xiaoyu Zhou,Yongtao Wang et al.
Yajiao Xiong et al.
We present DrivingGaussian++, an efficient and effective framework for realistic reconstruction and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background with incremental 3D Ga...
Qingyuan Zheng,Yue Liu,Yangbo He
Qingyuan Zheng
Causality plays a pivotal role in various fields of study. Based on the framework of causal graphical models, previous works have proposed identifying whether a variable is a cause or non-cause of another variable in every Markov equivalent...