Related papers: Zero-Shot Video Translation via Token Warping

Applying an image processing algorithm independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…

Current texture synthesis methods, which generate textures from fixed viewpoints, suffer from inconsistencies due to the lack of global context and geometric understanding. Meanwhile, recent advancements in video generation models have…

Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…

Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing…

Talking-head video editing aims to efficiently insert, delete, and substitute the word of a pre-recorded video through a text transcript editor. The key challenge for this task is obtaining an editing model that generates new talking-head…

Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external…

We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from images to video. While existing object-centric approaches…

Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time.…

Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either…

Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and image-to-video (I2V) models. However, like other AIGC types,…

Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue,…

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straightforward modeling…

Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This…

Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the…

Current diffusion-based video editing primarily focuses on structure-preserved editing by utilizing various dense correspondences to ensure temporal consistency and motion alignment. However, these approaches are often ineffective when the…

Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains.…

Diffusion-based world models have shown strong potential for unified world simulation, but the iterative denoising remains too costly for interactive use and long-horizon rollouts. While feature caching can accelerate inference without…

Existing video deraining methods are often trained on paired datasets, either synthetic, which limits their ability to generalize to real-world rain, or captured by static cameras, which restricts their effectiveness in dynamic scenes with…

We propose a method for adding sound-guided visual effects to specific regions of videos with a zero-shot setting. Animating the appearance of the visual effect is challenging because each frame of the edited video should have visual…

Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \textbf{1)} generalizable talking-face…