相关论文: Autoregression-free video prediction using diffusi…

We present a diffusion-based video editing framework, namely DiffusionAtlas, which can achieve both frame consistency and high fidelity in editing video object appearance. Despite the success in image editing, diffusion models still…

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

In recent years, large-scale pre-trained diffusion transformer models have made significant progress in video generation. While current DiT models can produce high-definition, high-frame-rate, and highly diverse videos, there is a lack of…

We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. FramePack compresses input frame contexts with frame-wise importance so that more frames can be encoded…

Autoregressive video models are promising for world modeling via next-frame prediction, but they suffer from exposure bias: a mismatch between training on clean contexts and inference on self-generated frames, causing errors to compound and…

Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due to the numerous sampling iterations required. To accelerate…

This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often…

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized…

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…

We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from…

This paper addresses the issue of modifying the visual appearance of videos while preserving their motion. A novel framework, named MagicProp, is proposed, which disentangles the video editing process into two stages: appearance editing and…

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not…

Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying…

Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promising alternative, though their advantages…

Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using information from neighboring frames, while completing masked…

Understanding how humans would behave during hand-object interaction is vital for applications in service robot manipulation and extended reality. To achieve this, some recent works have been proposed to simultaneously forecast hand…

Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion…

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token…

Most motion deblurring algorithms rely on spatial-domain convolution models, which struggle with the complex, non-linear blur arising from camera shake and object motion. In contrast, we propose a novel single-image deblurring approach that…