paper-with-me

홈 › Papers

Cross-Attention Transformer for Video Interpolation

2022-07-08 · Hannah Halin Kim, Shuzhi Yu, Shuai Yuan, Carlo Tomasi

We propose TAIN (Transformers and Attention for video INterpolation), a residual neural network for video interpolation, which aims to interpolate an intermediate frame given two consecutive image frames around it. We first present a novel vision transformer module, named Cross Similarity (CS), to globally aggregate input image features with similar appearance as those of the predicted interpolated frame. These CS features are then used to refine the interpolated prediction. To account for occlusions in the CS features, we propose an Image Attention (IA) module to allow the network to focus on CS features from one frame over those of the other. TAIN outperforms existing methods that do not require flow estimation and performs comparably to flow-based methods while being computationally efficient in terms of inference time on Vimeo90k, UCF101, and SNU-FILM benchmarks.

📄 PDF Abstract BibTeX arXiv:2207.04132

Code (1)

hannahhalin/tain 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Video Frame Interpolation with Flow Transformer

2023-07-30 · Pan Gao, Haoyue Tian, Jie Qin

Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generat…

Video Frame Interpolation

Video Frame Interpolation Transformer

2021-11-27 · CVPR 2022 1 · Zhihao Shi, Xiangyu Xu, Xiaohong Liu, Jun Chen 외

Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To addr…

Video Frame Interpolation

Video Frame Interpolation with Transformer

2022-05-15 · CVPR 2022 1 · Liying Lu, Ruizheng Wu, Huaijia Lin, Jiangbo Lu 외

Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years. Existing methods built upon convolut…

Video Frame Interpolation

EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation

2025-03-20 · CVPR 2025 1 · Zihao Zhang, Haoran Chen, Haoyu Zhao, Guansong Lu 외

Handling complex or nonlinear motion patterns has long posed challenges for video frame interpolation. Although recent advances in diffusion-based methods offer improvements over traditional optical flow-based approaches…

Optical Flow EstimationVideo Frame Interpolation

Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

2026-01-21 · Xinyu Peng, Han Li, Yuyang Huang, Ziyang Zheng 외 arxiv

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inconsistencies and motion artifacts. To ov…

Video Frame Interpolation