Related papers: Butterfly: Multiple Reference Frames Feature Propa…
We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to…
Deploying sparse Mixture of Experts(MoE) Vision Transformers remains a challenge due to linear expert memory scaling. Linear memory scaling stores $N$ independent expert weight matrices requiring $\mathcal{O}(N_E \cdot d^2)$ memory, which…
We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face…
The neural radiance fields (NeRF) have advanced the development of 3D volumetric video technology, but the large data volumes they involve pose significant challenges for storage and transmission. To address these problems, the existing…
Video compression is a central feature of the modern internet powering technologies from social media to video conferencing. While video compression continues to mature, for many compression settings, quality loss is still noticeable. These…
Learning based video compression attracts increasing attention in the past few years. The previous hybrid coding approaches rely on pixel space operations to reduce spatial and temporal redundancy, which may suffer from inaccurate motion…
Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented, which increases…
We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting…
Convolutional networks optimized for accuracy on challenging, dense prediction tasks are prohibitively slow to run on each frame in a video. The spatial similarity of nearby video frames, however, suggests opportunity to reuse computation.…
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…
While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The…
Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…
Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced…
Most of the existing neural video compression methods adopt the predictive coding framework, which first generates the predicted frame and then encodes its residue with the current frame. However, as for compression ratio, predictive coding…
We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the…
Neural Video Compression has emerged in recent years, with condition-based frameworks outperforming traditional codecs. However, most existing methods rely solely on the previous frame's features to predict temporal context, leading to two…
With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame codecs directly adopt P-frame coding tools without adequately…
In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely…
Storage systems often rely on multiple copies of the same compressed data, enabling recovery in case of binary data errors, of course, at the expense of a higher storage cost. In this paper we show that a wiser method of duplication entails…
Over the last decade, deep learning has shown great success at performing computer vision tasks, including classification, super-resolution, and style transfer. Now, we apply it to data compression to help build the next generation of…