相关论文: Learning for Video Compression with Recurrent Auto…
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…
Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression…
Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding…
With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of…
We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model. Our proposed model predicts 2D facial point heat maps regularized by both detection and regression loss, while uniquely…
This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders…
Variational autoencoders were proven successful in domains such as computer vision and speech processing. Their adoption for modeling user preferences is still unexplored, although recently it is starting to gain attention in the current…
Here we propose the Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE) method, a new iterative scheme that uses the deep learning framework of variational autoencoders to enhance sampling in molecular simulations. RAVE…
Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…
Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However,…
Recent developments in optical sensors enable a wide range of applications for multispectral imaging, e.g., in surveillance, optical sorting, and life-science instrumentation. Increasing spatial and spectral resolution allows creating…
Recurrent networks have been successful in analyzing temporal data and have been widely used for video analysis. However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features,…
Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing…
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems…
Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…
Sequence-to-sequence (Seq2seq) models have played an important role in the recent success of various natural language processing methods, such as machine translation, text summarization, and speech recognition. However, current Seq2seq…
Implicit neural representations store videos as neural networks and have performed well for various vision tasks such as video compression and denoising. With frame index or positional index as input, implicit representations (NeRV, E-NeRV,…
Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, however, mapping…
Neural Representations for Videos (NeRV) encode entire video sequences within neural network parameters, offering an alternative paradigm to conventional video codecs. However, the convolutional decoder of NeRV remains computationally…
Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the…