相关论文: World-Consistent Video-to-Video Synthesis

While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail to render correctly even short phrases or words and…

We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a…

Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without…

Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video…

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges,…

We present Stable Video 3D (SV3D) -- a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent work on 3D generation propose techniques to adapt 2D generative models for…

We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for…

Translation-based Video Synthesis (TVS) has emerged as a vital research area in computer vision, aiming to facilitate the transformation of videos between distinct domains while preserving both temporal continuity and underlying content…

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text…

Text-to-video (T2V) synthesis has advanced rapidly, yet current evaluation metrics primarily capture visual quality and temporal consistency, offering limited insight into how synthetic videos perform in downstream tasks such as…

Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in…

Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. Existing methods struggle to distinguishing between motion and structure, particularly in scenarios where camera poses are either unknown…

Text-to-image (T2I) diffusion models have revolutionized visual content creation, but extending these capabilities to text-to-video (T2V) generation remains a challenge, particularly in preserving temporal consistency. Existing methods that…

Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image…

In this study, we present an efficient and effective approach for achieving temporally consistent synthetic-to-real video translation in videos of varying lengths. Our method leverages off-the-shelf conditional image diffusion models,…

Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence…

Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the portrayed scene and, conversely, a…

Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcasting. However, existing implicit synthesis methods…

Videos of actions are complex signals containing rich compositional structure in space and time. Current video generation methods lack the ability to condition the generation on multiple coordinated and potentially simultaneous timed…