AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion

• URL: http://arxiv.org/abs/2503.07418v1
• Date: Mon, 10 Mar 2025 15:05:59 GMT
• Title: AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
• Authors: Mingzhen Sun, Weining Wang, Gen Li, Jiawei Liu, Jiahui Sun, Wanquan Feng, Shanshan Lao, SiYu Zhou, Qian He, Jing Liu,
• Abstract summary: We introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible video generation.<n>Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames.<n>This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence.
• Score: 19.98565541640125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge. However, asynchronous auto-regressive models often suffer from inconsistencies between training and inference, leading to issues such as error accumulation, while synchronous diffusion models are limited by their reliance on rigid sequence length. To address these issues, we introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible, asynchronous video generation. Specifically, our approach leverages diffusion to gradually corrupt video frames in both training and inference, reducing the discrepancy between these phases. Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames, ensuring that earlier frames remain clearer than subsequent ones. This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence. In addition, we design two specialized timestep schedulers: the FoPP scheduler for balanced timestep sampling during training, and the AD scheduler for flexible timestep differences during inference, supporting both synchronous and asynchronous generation. Extensive experiments demonstrate the superiority of our proposed method, which achieves competitive and state-of-the-art results across four challenging benchmarks.

Related papers

• READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation [55.58089937219475]
  We propose READ, the first real-time diffusion-transformer-based talking head generation framework.<n>Our approach first learns highly compressed video latent space via a VAE, significantly reducing the token count to speech generation.<n>We show that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime.
  arXiv  Detail & Related papers  (2025-08-05T13:57:03Z)
• Hybrid Autoregressive-Diffusion Model for Real-Time Streaming Sign Language Production [0.0]
  We introduce a hybrid approach combining autoregressive and diffusion models to generate Sign Language Production (SLP) models.<n>To capture fine-grained body movements, we design a Multi-Scale Pose Representation module that separately extracts detailed features from distinct arttors.<n>We also introduce a Confidence-Aware Causal Attention mechanism that utilizes joint-level confidence scores to dynamically guide the pose generation process.
  arXiv  Detail & Related papers  (2025-07-12T01:34:50Z)
• STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation [24.86836673853292]
  STAGE is an auto-regressive framework that pioneers hierarchical feature coordination and multiphase optimization for sustainable video synthesis.<n>HTFT enhances temporal consistency between video frames throughout the video generation process.<n>We generated 600 frames of high-quality driving videos on the Nuscenes dataset, which far exceeds the maximum length achievable by existing methods.
  arXiv  Detail & Related papers  (2025-06-16T06:53:05Z)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion [70.4360995984905]
  We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.<n>It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs.
  arXiv  Detail & Related papers  (2025-06-09T17:59:55Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [54.476056835275415]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• Fast Autoregressive Models for Continuous Latent Generation [49.079819389916764]
  Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP. Recent work, the masked autoregressive model (MAR) bypasses quantization by modeling per-token distributions in continuous spaces using a diffusion head. We propose Fast AutoRegressive model (FAR), a novel framework that replaces MAR's diffusion head with a lightweight shortcut head.
  arXiv  Detail & Related papers  (2025-04-24T13:57:08Z)
• Unifying Autoregressive and Diffusion-Based Sequence Generation [2.3923884480793673]
  We present extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions. Second, we propose two hybrid token-wise noising processes that interpolate between absorbing and uniform processes, enabling the model to fix past mistakes.
  arXiv  Detail & Related papers  (2025-04-08T20:32:10Z)
• MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space [40.60429652169086]
  Text-conditioned streaming motion generation requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths. We propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probabilistic autoregressive model.
  arXiv  Detail & Related papers  (2025-03-19T17:32:24Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  Diffusion Conditioned-based Gene Tokenizer replaces GAN-based decoder with conditional diffusion model.<n>We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch.<n>Even a scaled-down version of CDT (3$times$ inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes.<n>Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync [13.480681141520638]
  LatentSync is an end-to-end lip sync framework based on audio conditioned latent diffusion models without any intermediate motion representation.<n>Our framework can leverage the powerful capabilities of Stable Diffusion to model complex audio-visual correlations.<n>We significantly improve the accuracy of SyncNet from 91% to 94% on the HDTF test set.
  arXiv  Detail & Related papers  (2024-12-12T13:20:52Z)
• ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer [95.80384464922147]
  Continuous visual generation requires the full-sequence diffusion-based approach.<n>We present ACDiT, an Autoregressive blockwise Conditional Diffusion Transformer.<n>We demonstrate that ACDiT can be seamlessly used in visual understanding tasks despite being trained on the diffusion objective.
  arXiv  Detail & Related papers  (2024-12-10T18:13:20Z)
• Solving Video Inverse Problems Using Image Diffusion Models [58.464465016269614]
  We introduce an innovative video inverse solver that leverages only image diffusion models.<n>Our method treats the time dimension of a video as the batch dimension image diffusion models.<n>We also introduce a batch-consistent sampling strategy that encourages consistency across batches.
  arXiv  Detail & Related papers  (2024-09-04T09:48:27Z)
• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [64.2445487645478]
  Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio. We present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation.
  arXiv  Detail & Related papers  (2024-07-11T17:34:51Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)
• APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency [9.07931905323022]
  We propose a novel text-to-video (T2V) generation network structure based on diffusion models. Our approach only necessitates a single video as input and builds upon pre-trained stable diffusion networks. We leverage a hybrid architecture of transformers and convolutions to compensate for temporal intricacies, enhancing consistency between different frames within the video.
  arXiv  Detail & Related papers  (2023-08-24T07:11:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.