Related papers: Follow-Your-Motion: Video Motion Transfer via Effi…
Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and…
With the breakthrough of Transformer-based pre-trained models, the demand for fine-tuning (FT) to adapt the base pre-trained models to downstream applications continues to grow, so it is essential for service providers to reduce the cost of…
Image-to-video generation has made remarkable progress with the advancements in diffusion models, yet generating videos with realistic motion remains highly challenging. This difficulty arises from the complexity of accurately modeling…
The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion,…
While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic misalignment and kinematic artifacts. Through analysis, we…
Real-world low-resolution (LR) videos have diverse and complex degradations, imposing great challenges on video super-resolution (VSR) algorithms to reproduce their high-resolution (HR) counterparts with high quality. Recently, the…
Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…
Customized generation has achieved significant progress in image synthesis, yet personalized video generation remains challenging due to temporal inconsistencies and quality degradation. In this paper, we introduce CustomVideoX, an…
Image-conditioned Video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We study the…
Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative…
Generating temporally coherent, long-duration videos with precise control over subject identity and movement remains a fundamental challenge for contemporary diffusion-based models, which often suffer from identity drift and are limited to…
We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences. The main challenge of portrait animation is to preserve the identity of the reference…
Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…
In this paper, we aim to enhance the performance of SwiftBrush, a prominent one-step text-to-image diffusion model, to be competitive with its multi-step Stable Diffusion counterpart. Initially, we explore the quality-diversity trade-off…
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and…
Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with…
3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN- based methods necessitate datasets with balanced style distribution and content/style labels to train the clustered latent…
Existing person video generation methods either lack the flexibility in controlling both the appearance and motion, or fail to preserve detailed appearance and temporal consistency. In this paper, we tackle the problem of motion transfer…
Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…
Remote sensing change detection is often challenged by spatial misalignment between bi-temporal images, especially when acquisitions are separated by long seasonal or multi-year gaps. While modern convolutional and transformer-based models…