相关论文: Generative Memorize-Then-Recall framework for low …

Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could…

Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has proven effective as a global representation of scenes. However,…

Skeleton-based human action recognition is a powerful approach for understanding human behaviour from pose data, but collecting large-scale, diverse, and well-annotated 3D skeleton datasets is both expensive and labor-intensive. To address…

The introduction of multiple viewpoints in video scenes inevitably increases the bitrates required for storage and transmission. To reduce bitrates, researchers have developed methods to skip intermediate viewpoints during compression and…

Dense small objects in UAV imagery are often missed due to long-range viewpoints, occlusion, and clutter[cite: 5]. This paper presents a detector-agnostic post-processing framework that converts overlap-induced redundancy into group…

Learned video compression methods have gained a variety of interest in the video coding community since they have matched or even exceeded the rate-distortion (RD) performance of traditional video codecs. However, many current…

We propose a framework for learned image and video compression using the generative sparse visual representation (SVR) guided by fidelity-preserving controls. By embedding inputs into a discrete latent space spanned by learned visual…

Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their…

With a single eye fixation lasting a fraction of a second, the human visual system is capable of forming a rich representation of a complex environment, reaching a holistic understanding which facilitates object recognition and detection.…

Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video compression (e.g., H.264, MPEG-4) reduces superfluous…

This article proposes a method for mathematical modeling of human movements related to patient exercise episodes performed during physical therapy sessions by using artificial neural networks. The generative adversarial network structure is…

In this work, we introduce a two-step framework for generative modeling of temporal data. Specifically, the generative adversarial networks (GANs) setting is employed to generate synthetic scenes of moving objects. To do so, we propose a…

Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions. Temporally- and spatially-consistent, long-term world…

In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation…

In the latest years, videoconferencing has taken a fundamental role in interpersonal relations, both for personal and business purposes. Lossy video compression algorithms are the enabling technology for videoconferencing, as they reduce…

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…

Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart. With the rapid rise of deep learning, many recently proposed video super-resolution methods use convolutional neural networks in…

Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck…

Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural…

We propose a novel deep learning framework for animation video resequencing. Our system produces new video sequences by minimizing a perceptual distance of images from an existing animation video clip. To measure perceptual distance, we…