Related papers: StayStill: a large-scale 3D idle animation dataset
Image-to-video (I2V) generation seeks to produce realistic motion sequences from a single reference image. Although recent methods exhibit strong temporal consistency, they often struggle when dealing with complex, non-repetitive human…
Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models…
In recent years, we have seen an emergence of data-driven approaches in robotics. However, most existing efforts and datasets are either in simulation or focus on a single task in isolation such as grasping, pushing or poking. In order to…
Motions of virtual characters in movies or video games are typically generated by recording actors using motion capturing methods. Animations generated this way often need postprocessing, such as improving the periodicity of cyclic…
Vision is the richest and most cost-effective technology for Driver Monitoring Systems (DMS), especially after the recent success of Deep Learning (DL) methods. The lack of sufficiently large and comprehensive datasets is currently a…
In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions.…
"How can we animate 3D-characters from a movie script or move robots by simply telling them what we would like them to do?" "How unstructured and complex can we make a sentence and still generate plausible movements from it?" These are…
Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly in body size or position. We introduce StableAnimator++, the…
The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational…
This paper introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their…
Datasets advance research by posing challenging new problems and providing standardized methods of algorithm comparison. High-quality datasets exist for many important problems in robotics and computer vision, including egomotion estimation…
Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing…
We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remains challenging because highly dynamic human motion must be…
Linking human motion and natural language is of great interest for the generation of semantic representations of human activities as well as for the generation of robot activities based on natural language input. However, while there have…
Recent advances in world models have demonstrated strong capabilities in simulating physical reality, making them an increasingly important foundation for embodied intelligence. For UAV agents in particular, accurate prediction of complex…
Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations. (i) While the emphasis is on subject-centric prompts or static camera scenes, camera motion essential for producing cinematic…
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action…
We present a novel camera path optimization framework for the task of online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimating, path smoothing, and novel view rendering. Most previous…
Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying…
This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and…