Related papers: DIMO: Diverse 3D Motion Generation for Arbitrary O…
Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter,…
Human motion synthesis in complex scenes presents a fundamental challenge, extending beyond conventional Text-to-Motion tasks by requiring the integration of diverse modalities such as static environments, movable objects, natural language…
Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the…
We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to…
Spatio-temporal coherency is a major challenge in synthesizing high quality videos, particularly in synthesizing human videos that contain rich global and local deformations. To resolve this challenge, previous approaches have resorted to…
Modern video generators produce visually compelling clips but still struggle with physical and motion consistency, limiting their use as reliable world simulators. Existing remedies often rely on external simulators, teacher models, or…
Creating realistic 3D animation remains a time-consuming and expertise-dependent process, requiring manual rigging, keyframing, and fine-tuning of complex motions. Meanwhile, video diffusion models have recently demonstrated remarkable…
Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods often rely on 3D motion capture data, which requires special setups, resulting in high costs…
Image animation is the task of transferring the motion of a driving video to a given object in a source image. While great progress has recently been made in unsupervised motion transfer, requiring no labeled data or domain priors, many…
Modeling human behaviors in contextual environments has a wide range of applications in character animation, embodied AI, VR/AR, and robotics. In real-world scenarios, humans frequently interact with the environment and manipulate various…
The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural…
Video Generation is a relatively new and yet popular subject in machine learning due to its vast variety of potential applications and its numerous challenges. Current methods in Video Generation provide the user with little or no control…
Recovering high-quality 3D human motion in complex scenes from monocular videos is important for many applications, ranging from AR/VR to robotics. However, capturing realistic human-scene interactions, while dealing with occlusions and…
The motion of picking up and placing an object in 3D space is full of subtle detail. Typically these motions are formed from the same constraints, optimizing for swiftness, energy efficiency, as well as physiological limits. Yet, even for…
We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such motion requires solving a fundamental trade-off: generalizing…
We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use…
Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…
We present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone…
The "one-shot" technique represents a distinct and sophisticated aesthetic in filmmaking. However, its practical realization is often hindered by prohibitive costs and complex real-world constraints. Although emerging video generation…
We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing…