Related papers: Real-time Streaming Video Denoising with Bidirecti…
Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…
Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task. In this paper we propose a fully blind…
Video super-resolution (VSR) seeks to reconstruct high-resolution frames from low-resolution inputs. While diffusion-based methods have substantially improved perceptual quality, extending them to video remains challenging for two reasons:…
This paper presents a methodology for creating streaming, distributed inference algorithms for Bayesian nonparametric (BNP) models. In the proposed framework, processing nodes receive a sequence of data minibatches, compute a variational…
Video summarization aims to eliminate visual redundancy while retaining key parts of video to construct concise and comprehensive synopses. Most existing methods use discriminative models to predict the importance scores of video frames.…
Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing…
Recent advances in diffusion models have greatly improved text-driven video generation. However, training models for long video generation demands significant computational power and extensive data, leading most video diffusion models to be…
Surgical video datasets are essential for scene understanding, enabling procedural modeling and intra-operative support. However, these datasets are often heavily imbalanced, with rare actions and tools under-represented, which limits the…
Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet, the most powerful video understanding models are too…
Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…
With the widespread deployment of video surveillance devices and the demand for intelligent system development, video anomaly detection (VAD) has become an important part of constructing intelligent surveillance systems. Expanding the…
Video super-resolution (VSR) aims to estimate a high-resolution (HR) frame from a low-resolution (LR) frames. The key challenge for VSR lies in the effective exploitation of spatial correlation in an intra-frame and temporal dependency…
Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…
Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal…
Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…
Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…
Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception…
Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. We introduce DiViD,…
Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers…