Related papers: Decoupling Contact for Fine-Grained Motion Style T…
We propose a novel, zero-shot image generation technique called "Visual Concept Blending" that provides fine-grained control over which features from multiple reference images are transferred to a source image. If only a single reference…
We introduce a novel Stylized Motion Diffusion model, dubbed SMooDi, to generate stylized motion driven by content texts and style motion sequences. Unlike existing methods that either generate motion of various content or transfer style…
Tactile sensing can provide access to information about the contact (i.e. slippage, surface feature, friction), which is out of reach of vision but crucial for manipulation. To access this information, a dense measurement of the deformation…
We present a system for non-prehensile manipulation that require a significant number of contact mode transitions and the use of environmental contacts to successfully manipulate an object to a target location. Our method is based on deep…
This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle…
When we physically interact with our environment using our hands, we touch objects and force them to move: contact and motion are defining properties of manipulation. In this paper, we present an active, bottom-up method for the detection…
Hands are the main medium when people interact with the world. Generating proper 3D motion for hand-object interaction is vital for applications such as virtual reality and robotics. Although grasp tracking or object manipulation synthesis…
Non-prehensile manipulation enables fast interactions with objects by circumventing the need to grasp and ungrasp as well as handling objects that cannot be grasped through force closure. Current approaches to non-prehensile manipulation…
Inferring plausible node mobility based only on information from wireless contact traces is a difficult problem. Working with mobility information allows richer protocol simulations, particularly in dense networks, but requires complex…
Image style transfer is a challenging task in computational vision. Existing algorithms transfer the color and texture of style images by controlling the neural network's feature layers. However, they fail to control the strength of…
As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally…
Humans interact with an object in many different ways by making contact at different locations, creating a highly complex motion space that can be difficult to learn, particularly when synthesizing such human interactions in a controllable…
We introduce a real-time, human-in-the-loop gesture control framework that can dynamically adapt audio and music based on human movement by analyzing live video input. By creating a responsive connection between visual and auditory stimuli,…
Motion in-betweening is a crucial tool for animators, enabling intricate control over pose-level details in each keyframe. Recent machine learning solutions for motion in-betweening rely on complex models, incorporating skeleton-aware…
Image-conditioned Video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We study the…
Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video…
In the past, manually re-drawing an image in a certain artistic style required a professional artist and a long time. Doing this for a video sequence single-handed was beyond imagination. Nowadays computers provide new possibilities. We…
Robotic manipulation in space is essential for emerging applications such as debris removal and in-space servicing, assembly, and manufacturing (ISAM). A key requirement for these tasks is the ability to perform precise, contact-rich…
Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangled motion control, allowing users to separately control the…
This paper presents a correspondence-free, function-based sim-to-real learning method for controlling deformable freeform surfaces. Unlike traditional sim-to-real transfer methods that strongly rely on marker points with full…