Related papers: Brick-Diffusion: Generating Long Videos with Brick…
Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…
Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…
Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high…
Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making…
We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods…
Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…
Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices.…
Large-scale text-to-video (T2V) diffusion models have great progress in recent years in terms of visual quality, motion and temporal consistency. However, the generation process is still a black box, where all attributes (e.g., appearance,…
Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…
We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of…
Diffusion models have emerged as frontrunners in text-to-image generation, but their fixed image resolution during training often leads to challenges in high-resolution image generation, such as semantic deviations and object replication.…
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…
Generating long, high-quality videos remains a challenge due to the complex interplay of spatial and temporal dynamics and hardware limitations. In this work, we introduce MaskFlow, a unified video generation framework that combines…
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical…
We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain scenario diversity over long durations presents significant…
Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to…
Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…
We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…