Related papers: Vectorized Video Representation with Easy Editing …
Text-guided video-to-video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text-guided image diffusion models can be extended for stylized video synthesis.…
Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic…
Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing…
The alignment of representations from different modalities has recently been shown to provide insights on the structural similarities and downstream capabilities of different encoders across diverse data types. While significant progress…
There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously…
Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use…
Vector graphics, known for their scalability and user-friendliness, provide a unique approach to visual content compared to traditional pixel-based images. Animation of these graphics, driven by the motion of their elements, offers enhanced…
Accurate future video prediction requires both high visual fidelity and consistent scene semantics, particularly in complex dynamic environments such as autonomous driving. We present Re2Pix, a hierarchical video prediction framework that…
We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
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…
Video anomaly detection (VAD) is an important but challenging task in computer vision. The main challenge rises due to the rarity of training samples to model all anomaly cases. Hence, semi-supervised anomaly detection methods have gotten…
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…
Neural Representations for Videos (NeRV) has emerged as a promising implicit neural representation (INR) approach for video analysis, which represents videos as neural networks with frame indexes as inputs. However, NeRV-based methods are…
We address image-to-video generation with explicit user control over the final frame's disoccluded regions. Current image-to-video pipelines produce plausible motion but struggle to generate predictable, articulated motions while enforcing…
This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
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…
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…