Related papers: Time-Correlated Video Bridge Matching
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
In the context of human action recognition in video sequences, a temporal belief filter is presented. It allows to cope with human action disparity and low quality videos. The whole system of action recognition is based on the Transferable…
Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control. Prior methods for motion-conditioned synthesis typically require model-specific…
This work introduces \textbf{VideoMark}, a distortion-free robust watermarking framework for video diffusion models. As diffusion models excel in generating realistic videos, reliable content attribution is increasingly critical. However,…
Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions…
Video prediction is a useful function for autonomous driving, enabling intelligent vehicles to reliably anticipate how driving scenes will evolve and thereby supporting reasoning and safer planning. However, existing models are constrained…
Bridge models in image restoration construct a diffusion process from degraded to clear images. However, existing methods typically require training a bridge model from scratch for each specific type of degradation, resulting in high…
Recently, diffusion models have gained significant attention as a novel set of deep learning-based generative methods. These models attempt to sample data from a Gaussian distribution that adheres to a target distribution, and have been…
Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion. Optical flow supervision is a promising approach to address this, with prior works commonly employing…
Diffusion models have achieved huge empirical success in data generation tasks. Recently, some efforts have been made to adapt the framework of diffusion models to discrete state space, providing a more natural approach for modeling…
Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context…
Generating long and consistent videos has emerged as a significant yet challenging problem. While most existing diffusion-based video generation models, derived from image generation models, demonstrate promising performance in generating…
We propose simple methods for multivariate diffusion bridge simulation, which plays a fundamental role in simulation-based likelihood and Bayesian inference for stochastic differential equations. By a novel application of classical coupling…
Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generative modeling methods have been proposed and demonstrated…
Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video…
Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data. Existing compositional approaches stitch together short segments…
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural…
In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form…
Cross-domain time series imputation is an underexplored data-centric research task that presents significant challenges, particularly when the target domain suffers from high missing rates and domain shifts in temporal dynamics. Existing…
World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and…