相关论文: Implicit Stacked Autoregressive Model for Video Pr…

A defining characteristic of intelligent systems is the ability to make action decisions based on the anticipated outcomes. Video prediction systems have been demonstrated as a solution for predicting how the future will unfold visually,…

Recent advancements in generative models have ignited substantial interest in dynamic 3D content creation (\ie, 4D generation). Existing approaches primarily rely on Score Distillation Sampling (SDS) to infer novel-view videos, typically…

This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propose a sampling…

MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predictors tend to…

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

Video prediction is a crucial task for intelligent agents such as robots and autonomous vehicles, since it enables them to anticipate and act early on time-critical incidents. State-of-the-art video prediction methods typically model the…

A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their appearances across frames. This work introduces an…

Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…

Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on…

Inter prediction is a key technology to reduce the temporal redundancy in video coding. In natural videos, there are usually multiple moving objects with variable velocity, resulting in complex motion fields that are difficult to represent…

We introduce here a predictive coding based model that aims to generate accurate and sharp future frames. Inspired by the predictive coding hypothesis and related works, the total model is updated through a combination of bottom-up and…

Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in…

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

The scarcity of manipulation data has motivated the use of pretrained large models from other modalities in robotics. In this work, we build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR), where…

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the…

Next-Token Prediction (NTP) is a de facto approach for autoregressive (AR) video generation, but it suffers from suboptimal unidirectional dependencies and slow inference speed. In this work, we propose a semi-autoregressive (semi-AR)…

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has…

Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to…

The forecasting of multi-variate time processes through graph-based techniques has recently been addressed under the graph signal processing framework. However, problems in the representation and the processing arise when each time series…

Motion prediction for intelligent vehicles typically focuses on estimating the most probable future evolutions of a traffic scenario. Estimating the gap acceptance, i.e., whether a vehicle merges or crosses before another vehicle with the…