New method tackles video inverse problems using image diffusion models.
problem Spatio-temporal degradation in video inverse problems.
method Leverages image diffusion models to treat time dimension as batch dimension, introduces batch-consistent diffusion sampling.
result Achieves state-of-the-art reconstructions for various spatio-temporal degradations.
RaMViD uses diffusion models for video prediction and infilling.
problem Predicting and infilling missing information in videos.
method Extends image diffusion models to videos using 3D convolutions and a new conditioning technique.
result Achieves state-of-the-art results on video prediction benchmarks.
Paper presents a new video generation model using diffusion probabilistic methods.
problem Generating high-quality video sequences.
method Denoising diffusion probabilistic models, autoregressive, end-to-end optimization.
result Significant improvements in perceptual quality and probabilistic frame forecasting.
Rolling Diffusion improves video prediction by progressively corrupting frames based on their temporal position.
problem Improving video prediction accuracy by accounting for temporal dynamics.
method A sliding window denoising process that assigns more noise to frames that appear later in a sequence.
result Rolling Diffusion outperforms standard diffusion models in tasks with complex temporal dynamics.
VISION-XL improves HD video quality using latent image diffusion models.
problem Improving high-definition video quality and resolution.
method Latent image diffusion models and pseudo-batch consistent sampling.
result State-of-the-art video reconstruction across various inverse problems.
LVTINO improves high-definition video restoration with consistent temporal details.
problem Restoring high-definition video with fine spatial detail and temporal consistency.
method LVTINO uses Video Consistency Models to bypass frame-by-frame image-based LDMs, achieving perceptual quality and computational efficiency.
result Significant perceptual improvements over current methods, achieving state-of-the-art quality with minimal evaluations.
New method improves local precipitation predictions using video diffusion.
problem Limited high-resolution local precipitation predictions due to computational costs.
method Extends video diffusion models to capture conditional distribution of high-resolution patterns.
result Method outperforms state-of-the-art baselines in CRPS, MSE, and precipitation distribution.
A new video prediction model treats videos as continuous processes, reducing sampling steps and improving efficiency.
problem Efficiency and temporal coherence in video prediction models.
method Treats videos as a continuous multi-dimensional process, reducing sampling steps.
result Reduction of 75% sampling steps, state-of-the-art performance on benchmark datasets.
Ground-A-Video edits videos without training, preserving intended changes.
problem Complex multi-attribute video editing with omitted or wrong changes.
method Grounding-guided video-to-video translation with Cross-Frame Gated Attention.
result Zero-shot multi-attribute video editing with improved accuracy and frame consistency.
New method converts video of dye plumes into PDEs for better understanding.
problem Inferring continuum models from uncalibrated video data.
method Develops a pipeline to convert grayscale recordings into scalar fields, isolates drift, and identifies transport laws.
result Selected reduced model outperforms advection-diffusion baselines and retains structural interpretability.
Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.
problem Enhancing robotic manipulation through robust and multi-modal learning.
method Probabilistic diffusion models integrating imitation and reinforcement learning.
result Diffusion models improve grasp learning, trajectory planning, and data augmentation in robotics.
This research explores how different discrete diffusion kernels affect graph generation quality.
problem The impact of different discrete diffusion kernels on graph generation quality.
method Developed a family of discrete diffusion kernels that converge to different Bernoulli priors.
result The quality of generated graphs is sensitive to the prior used, challenging previous intuitions.
Generative model handles varying data dimensions using jump diffusion processes.
problem Handling data of varying dimensionality in generative models.
method Formulated as a jump diffusion process, learning to approximate the process with a novel evidence lower bound.
result Effective sampling of data of varying dimensionality, better compatibility with test-time diffusion guidance imputation tasks.
Diffusion Transformer captures spatial-temporal dependencies in sequential data.
problem Capturing rich spatial and temporal dependencies in sequential data.
method Established theoretical guarantees for diffusion transformers learning Gaussian process data.
result Spatial-temporal dependencies are captured within attention layers of diffusion transformers.
In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it provides flexible Hawkes kernels and quantifies their uncertainty. Our method is based on the cluster representation of Hawkes processes. Util…
Shallow diffusion models learn hidden low-dimensional structures effectively.
problem Learning from high-dimensional signals like images and video.
method Analysis of shallow diffusion models over the Barron space of single layer neural networks.
result Shallow diffusion models can adapt to simple low-dimensional structures, overcoming the curse of dimensionality.
Auto-regressive diffusion models improve capturing conditional dependence in data.
problem Vanilla diffusion models struggle to capture important, high-level relationships in real-world data.
method Developed auto-regressive diffusion models to better capture conditional dependence structures.
result AR diffusion models produce samples with a reduced gap in approximating the data conditional distribution.
New method speeds up diffusion models without sacrificing quality.
problem Slow inference in diffusion models.
method Adams-Bashforth method for caching and acceleration.
result Achieved nearly 3x speedup with maintained quality.
Study shows diffusion models adapt to manifold hypothesis without dimensionality issues.
problem Empirical success of diffusion models in high-dimensional data.
method Developed a new framework connecting diffusion models to Gaussian Processes theory.
result Achieves rates independent of ambient dimension in terms of score learning and sampling complexity.
SAMI learns disentangled representations from data.
problem Learning disentangled representations from data.
method Combines diffusion models and VAEs to learn disentangled representations.
result SAMI learns disentangled representations that are interpretable and useful.
New AI method generates SDE paths without explicit coefficients.
problem Simulating unknown Markovian SDEs with limited data.
method Uses conditional diffusion models on sample paths.
result Consistently outperforms alternative methods in KL divergence.
FunDiff models physical functions using diffusion and autoencoders.
problem Adapting generative models to continuous physical functions.
method Combines latent diffusion with function autoencoder, enforcing physical priors.
result Achieves optimal convergence rates for physical function estimation.
daep learns from irregular, multimodal astronomical data.
problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.
A new method optimizes diffusion models with recursive likelihood ratios.
problem Efficiently aligning pre-trained diffusion models for specific applications.
method Recursive Likelihood Ratio (RLR) optimizer for Half-Order (HO) fine-tuning.
result The RLR method achieves unbiased and lower-variance gradients, improving model performance.
This research explores discrete diffusion models for natural language generation.
problem Challenges in applying diffusion models to discrete data, especially natural language.
method Investigates Discrete Denoising Diffusion Probabilistic Model (D3PM) and compares it with autoregressive models.
result Discrete diffusion models achieve better processing speed than autoregressive models.
Consistency models generate high-quality samples fast and without iterative sampling.
problem Slow generation in diffusion models.
method Direct mapping of noise to data, supporting fast one-step generation and multistep sampling.
result Consistency models achieve state-of-the-art FID scores and outperform diffusion models in one-step generation.
New optimal rates for score estimation improve diffusion model performance.
problem Improving statistical rates for score estimation in diffusion models.
method Sharp minimax rates for score estimation of diffused distributions.
result Achieves sharp minimax rate without extraneous logarithmic terms.
Generative AI tasks analyzed for text, images, audio, video, code, and molecules.
problem What is the core question when using generative AI?
method Survey of generative model families, probabilistic framework, game-theoretic setup, post-training modifications, socially responsible considerations.
result Generative AI is a distinct machine learning task with connections to prediction, compression, and decision-making.
Current deep learning results on video generation are limited while there are only a few first results on video prediction and no relevant significant results on video completion. This is due to the severe ill-posedness inherent in these three problems. In this paper, we focus on human action videos, and propose a gene…
Improves video search by balancing text and visual modalities.
problem Modality imbalance in video search models, focusing mainly on text matching.
method Proposes MBVR with MS samples and DM to balance modalities.
result Empirically shows significant improvement in modality balance and search effectiveness.
UDVD uses deep learning to denoise videos without supervision.
problem Lack of clean video data for training deep learning models.
method UDVD is a CNN trained solely on noisy video data, adapting to local motion.
result UDVD performs as well as supervised methods, even with limited training data.
We develop a variational framework for SDEs driven by fractional noise.
problem Capturing long-term dependencies in SDEs driven by fractional noise.
method Markov approximation of fractional Brownian motion, variational inference, neural networks.
result Efficient variational inference of posterior path measures for neural-SDEs.
Paper proposes SMFN for high-res spherical video super-resolution.
problem Super-resolution of 360-degree panoramic videos is expensive and challenging.
method Deformable convolutions, mixed attention mechanism, dual learning strategy, weighted mean square error loss function.
result The proposed SMFN method improves super-resolution of equatorial regions in 360-degree videos.
DDMI generates high-quality INRs by adapting positional embeddings.
problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.
Paper proposes new principles and framework for AVC learning from user-generated videos.
problem Challenges in learning audio-visual correspondence from short-term user-generated videos.
method Introduced new principles and a framework to facilitate AVC learning from videos' themes.
result Proposed approach outperformed baseline by 23.15% on KWAI-AD-AudVis corpus.
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their composi…
The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, the generation becomes increasingly challenging with the incre…
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a mod…
Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the well-trained models output wrong labels with high confidence. In this pap…
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their composi…
With the growth of user-generated content, we observe the constant rise of the number of companies, such as search engines, content aggregators, etc., that operate with tremendous amounts of web content not being the services hosting it. Thus, aiming to locate the most important content and promote it to the users, the…
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
Video summarisation can be posed as the task of extracting important parts of a video in order to create an informative summary of what occurred in the video. In this paper we introduce SummaryNet as a supervised learning framework for automated video summarisation. SummaryNet employs a two-stream convolutional network…
Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet-of-Things applications, surveillance systems and semantic crawlers of la…
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of subs…
Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…
C3 compresses images and videos with low complexity and high performance.
problem High complexity and low performance in neural compression models.
method Overfits a small model to each image or video separately, improving RD performance with low complexity.
result Matches the RD performance of state-of-the-art neural and video codecs with significantly lower decoding complexity.