Related papers: NVC-1B: A Large Neural Video Coding Model
With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…
To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can…
Large models have achieved remarkable performance across various tasks, yet they incur significant computational costs and privacy concerns during both training and inference. Distributed deployment has emerged as a potential solution, but…
Perceptual video compression adopts generative video modeling to improve perceptual realism but frequently sacrifices signal fidelity, diverging from the goal of video compression to faithfully reproduce visual signal. To alleviate the…
The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware representation and lifelike synthesis. Generative Face Video Coding…
Recent advances in visual generation have made significant strides in producing content of exceptional quality. However, most methods suffer from a fundamental problem - a bottleneck of inference computational efficiency. Most of these…
Good quality video coding for low bit-rate applications is important for transmission over narrow-bandwidth channels and for storage with limited memory capacity. In this work, we develop a previous analysis for image compression at low…
Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of…
Video Captioning (VC) is a challenging multi-modal task since it requires describing the scene in language by understanding various and complex videos. For machines, the traditional VC follows the…
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost…
Recent advancements in deep learning techniques have significantly improved the quality of compressed videos. However, previous approaches have not fully exploited the motion characteristics of compressed videos, such as the drastic change…
Recently, deep image compression has shown a big progress in terms of coding efficiency and image quality improvement. However, relatively less attention has been put on video compression using deep learning networks. In the paper, we first…
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…
Video post-processing methods can improve the quality of compressed videos at the decoder side. Most of the existing methods need to train corresponding models for compressed videos with different quantization parameters to improve the…
Human motion modeling is a classic problem in computer vision and graphics. Challenges in modeling human motion include high dimensional prediction as well as extremely complicated dynamics.We present a novel approach to human motion…
Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either provide imprecise camera control from text prompts or rely on labor-intensive manual…
Video coding is a video compression technique that compresses the original video sequence to produce a smaller archive file or reduce the transmission bandwidth under constraints on the visual quality loss. Rate control (RC) plays a…
While going deeper has been witnessed to improve the performance of convolutional neural networks (CNN), going smaller for CNN has received increasing attention recently due to its attractiveness for mobile/embedded applications. It remains…
Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…
The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…