Related papers: Learning to Compress Videos without Computing Moti…
Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to their difficulty…
Experience and reasoning occur across multiple temporal scales: milliseconds, seconds, hours or days. The vast majority of computer vision research, however, still focuses on individual images or short videos lasting only a few seconds.…
Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…
Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as…
The past few years have witnessed great success in applying deep learning to enhance the quality of compressed image/video. The existing approaches mainly focus on enhancing the quality of a single frame, ignoring the similarity between…
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a…
Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable…
Video-quality measurement is a critical task in video processing. Nowadays, many implementations of new encoding standards - such as AV1, VVC, and LCEVC - use deep-learning-based decoding algorithms with perceptual metrics that serve as…
Visual language models encounter challenges in computational efficiency and latency, primarily due to the substantial redundancy in the token representations of high-resolution images and videos. Current attention/similarity-based…
Virtual Reality (VR) has the potential of becoming the next ubiquitous computing platform. Continued progress in the burgeoning field of VR depends critically on an efficient computing substrate. In particular, DRAM access energy is known…
The non-uniformly distributed nature of the 3D dynamic point cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud…
Video semantic segmentation (VSS) is a computationally expensive task due to the per-frame prediction for videos of high frame rates. In recent work, compact models or adaptive network strategies have been proposed for efficient VSS.…
This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM). In this paper, the traditional optimization methods adaptively adjust the…
This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…
With the rapid proliferation of the Internet of Things, video analytics has become a cornerstone application in wireless multimedia sensor networks. To support such applications under bandwidth constraints, learning-based adaptive…
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 task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…
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…
Video-to-video translation aims to generate video frames of a target domain from an input video. Despite its usefulness, the existing networks require enormous computations, necessitating their model compression for wide use. While there…
Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization,…