Related papers: DIVE: Taming DINO for Subject-Driven Video Editing
Instruction-based image editing models offer increased personalization opportunities in generative tasks. However, properly evaluating their results is challenging, and most of the existing metrics lag in terms of alignment with human…
Image-driven video editing aims to propagate edit contents from the modified first frame to the remaining frames. Existing methods usually invert the source video to noise using a pre-trained image-to-video (I2V) model and then guide the…
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework…
Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of…
The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we…
Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios…
Large-scale text-to-image diffusion models have achieved unprecedented success in image generation and editing. However, extending this success to video editing remains challenging. Recent video editing efforts have adapted pretrained…
Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos,…
Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing…
Temporal consistency is essential for video editing applications. Existing work on layered representation of videos allows propagating edits consistently to each frame. These methods, however, can only edit object appearance rather than…
Dynamic scene video deblurring aims to remove undesirable blurry artifacts captured during the exposure process. Although previous video deblurring methods have achieved impressive results, they suffer from significant performance drops due…
Point tracking aims to localize corresponding points across video frames, serving as a fundamental task for 4D reconstruction, robotics, and video editing. Existing methods commonly rely on shallow convolutional backbones such as ResNet…
Text-driven 3D editing enables user-friendly 3D object or scene editing with text instructions. Due to the lack of multi-view consistency priors, existing methods typically resort to employing 2D generation or editing models to process each…
While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance…
Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level") depicting a single scene. To deliver a coherent long video…
Training-free video editing (VE) models tend to fall back on gender stereotypes when rendering profession-related prompts. We propose \textbf{FAME} for \textit{Fairness-aware Attention-modulated Video Editing} that mitigates…
The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…
The rapid advancement in visual generation, particularly the emergence of pre-trained text-to-image and text-to-video models, has catalyzed growing interest in training-free video editing research. Mirroring training-free image editing…
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…
Video editing serves as a fundamental pillar of digital media, spanning applications in entertainment, education, and professional communication. However, previous methods often overlook the necessity of comprehensively understanding both…