相关论文: Uni-Animator: Towards Unified Visual Colorization
Simulating physically realistic garment deformations is an essential task for virtual immersive experience, which is often achieved by physics simulation methods. However, these methods are typically time-consuming, computationally…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…
We present X-UniMotion, a unified and expressive implicit latent representation for whole-body human motion, encompassing facial expressions, body poses, and hand gestures. Unlike prior motion transfer methods that rely on explicit skeletal…
Video generation is a challenging yet pivotal task in various industries, such as gaming, e-commerce, and advertising. One significant unresolved aspect within T2V is the effective visualization of text within generated videos. Despite the…
We present Animated Vega-Lite, a set of extensions to Vega-Lite that model animated visualizations as time-varying data queries. In contrast to alternate approaches for specifying animated visualizations, which prize a highly expressive…
Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods…
Video compositing combines live-action footage to create video production, serving as a crucial technique in video creation and film production. Traditional pipelines require intensive labor efforts and expert collaboration, resulting in…
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a…
Text-guided diffusion models have achieved remarkable success in object inpainting by providing high-level semantic guidance through text prompts. However, they often lack precise pixel-level spatial control, especially in scenarios…
Visual correspondence is a fundamental building block on the way to building assistive tools for hand-drawn animation. However, while a large body of work has focused on learning visual correspondences at the pixel-level, few approaches…
Recent video inpainting methods have made remarkable progress by utilizing explicit guidance, such as optical flow, to propagate cross-frame pixels. However, there are cases where cross-frame recurrence of the masked video is not available,…
Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the…
Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color differences, and occlusion. To address these issues, we…
Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains…
With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…
Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image editing and video synthesis. Despite their formidable…
Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variations in the spatial scale and difficulties of recognition…
Large-scale text-to-video (T2V) diffusion models have great progress in recent years in terms of visual quality, motion and temporal consistency. However, the generation process is still a black box, where all attributes (e.g., appearance,…
Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free…