相关论文: Scaling Zero-Shot Reference-to-Video Generation

Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs…

Audio to Video generation is an interesting problem that has numerous applications across industry verticals including film making, multi-media, marketing, education and others. High-quality video generation with expressive facial movements…

Subject-driven video generation (SDV-Gen) aims to produce videos of a specific subject by adapting a pretrained video model, enabling personalized and application-driven content creation. To achieve this goal, per-subject tuning methods…

Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V…

Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error,…

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V)…

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on.…

Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is drinking water."). Existing TI2V frameworks often require…

Event-based cameras offer unique advantages such as high temporal resolution, high dynamic range, and low power consumption. However, the massive storage requirements and I/O burdens of existing synthetic data generation pipelines and the…

We present Kaleido, a subject-to-video~(S2V) generation framework, which aims to synthesize subject-consistent videos conditioned on multiple reference images of target subjects. Despite recent progress in S2V generation models, existing…

We present SUGAR, a zero-shot method for subject-driven video customization. Given an input image, SUGAR is capable of generating videos for the subject contained in the image and aligning the generation with arbitrary visual attributes…

Text-to-video (T2V) models have shown remarkable capabilities in generating diverse videos. However, they struggle to produce user-desired stylized videos due to (i) text's inherent clumsiness in expressing specific styles and (ii) the…

Recent advances in customized video generation have enabled users to create videos tailored to both specific subjects and motion trajectories. However, existing methods often require complicated test-time fine-tuning and struggle with…

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without…

Adapting image models to the video domain has emerged as an efficient paradigm for solving video recognition tasks. Due to the huge number of parameters and effective transferability of image models, performing full fine-tuning is less…

The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative adversarial networks (GANs). In this paper, we propose RL-V2V-GAN, a new deep neural…

Zero-shot referring image segmentation is a challenging task because it aims to find an instance segmentation mask based on the given referring descriptions, without training on this type of paired data. Current zero-shot methods mainly…

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset.…

Reference-based Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image or video by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly…

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…