相关论文: Separate Motion from Appearance: Customizing Motio…
Text-to-motion models that generate sequences of human poses from textual descriptions are garnering significant attention. However, due to data scarcity, the range of motions these models can produce is still limited. For instance, current…
Generating 3D human motion from text descriptions remains challenging due to the diverse and complex nature of human motion. While existing methods excel within the training distribution, they often struggle with out-of-distribution…
Human motion generation is essential for fields such as animation, robotics, and virtual reality, requiring models that effectively capture motion dynamics from text descriptions. Existing approaches often rely on Contrastive Language-Image…
Video prediction is a useful function for autonomous driving, enabling intelligent vehicles to reliably anticipate how driving scenes will evolve and thereby supporting reasoning and safer planning. However, existing models are constrained…
Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-specific appearance and motion from a single video, is now…
Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing…
Traffic videos inherently differ from generic videos in their stationary camera setup, thus providing a strong motion prior where objects often move in a specific direction over a short time interval. Existing works predominantly employ…
We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…
Distilled video generation models offer fast and efficient synthesis but struggle with motion customization when guided by reference videos, especially under training-free settings. Existing training-free methods, originally designed for…
Personalized text-to-image generation aims to synthesize images of user-provided concepts in diverse contexts. Despite recent progress in multi-concept personalization, most are limited to object concepts and struggle to customize abstract…
Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wearable alternatives also suffer from noisy or unstable data,…
Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…
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…
Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…
We focus on the problem of using generative diffusion models for the task of motion detailing: converting a rough version of a character animation, represented by a sparse set of coarsely posed, and imprecisely timed blocking poses, into a…
Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…
Text-to-motion generation is a crucial task in computer vision, which generates the target 3D motion by the given text. The existing annotated datasets are limited in scale, resulting in most existing methods overfitting to the small…
Generating human motion from textual descriptions is a challenging task. Existing methods either struggle with physical credibility or are limited by the complexities of physics simulations. In this paper, we present \emph{ReinDiffuse} that…
Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult…
Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…