Related papers: A Lightweight Dual-Mode Optimization for Generativ…
Versatile Video Coding (VVC) allows for large compression efficiency gains over its predecessor, High Efficiency Video Coding (HEVC). The added efficiency comes at the cost of increased runtime complexity, especially for encoding. It is…
We present GNVC-VD, the first DiT-based generative neural video compression framework built upon an advanced video generation foundation model, where spatio-temporal latent compression and sequence-level generative refinement are unified…
The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…
While learned video codecs have demonstrated great promise, they have yet to achieve sufficient efficiency for practical deployment. In this work, we propose several novel ideas for learned video compression which allow for improved…
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional…
Generative model based compact video compression is typically operated within a relative narrow range of bitrates, and often with an emphasis on ultra-low rate applications. There has been an increasing consensus in the video communication…
As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…
Recent deep-learning-based video compression methods brought coding gains over conventional codecs such as AVC and HEVC. However, learning-based codecs generally require considerable computation time and model complexity. In this paper, we…
Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such schemes often face the…
Recently, the deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. However, a challenge of many learning-based approaches is that they often achieve…
Vector Quantization (VQ) techniques face significant challenges in codebook utilization, limiting reconstruction fidelity in image modeling. We introduce a Dual Codebook mechanism that effectively addresses this limitation by partitioning…
Structured channel pruning has been shown to significantly accelerate inference time for convolution neural networks (CNNs) on modern hardware, with a relatively minor loss of network accuracy. Recent works permanently zero these channels…
Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and…
This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) performance. Unlike the standard convolution, GConv first selects…
In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended…
Nowadays, more and more video transmissions primarily aim at downstream machine vision tasks rather than humans. While widely deployed Human Visual System (HVS) oriented video coding standards like H.265/HEVC and H.264/AVC are efficient,…
The versatility of recent machine learning approaches makes them ideal for improvement of next generation video compression solutions. Unfortunately, these approaches typically bring significant increases in computational complexity and are…
Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…
Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a…
Deepfakes have raised significant concerns due to their potential to spread false information and compromise digital media integrity. Current deepfake detection models often struggle to generalize across a diverse range of deepfake…