We propose CLIP-Actor-X, a text-driven motion generation and neural mesh stylization system for 4D human avatar generation. CLIP-Actor-X generates a detailed 3D human mesh, motion animation, and texture to conform to a given text prompt input from a user. CLIP- Actor-X system mainly consists of two modules. First, for generating realistic human motion, we build a text-driven human motion synthesis module modeled by a retrieval-augmented generative model, powered by a text-to-motion diffusion model. Second, our novel zero-shot neural style optimization module detailizes and texturizes the sampled sequence of a neutral human mesh template, such that the resulting mesh and appearance comply with the input text prompt in a temporally-consistent and pose-agnostic manner. In contrast to the prior arts that use an artist-designed, non-animatable mesh as an input, our output representation is animatable and better aligned between an input text and the generated avatar without additional post-processes, e.g., re-alignment, retargeting, or rigging. We further propose the ways to stabilize the optimization process: spatio-temporal view augmentation and visibility-aware embedding attention, which deals with poorly rendered views. We demonstrate that CLIP-Actor-X produces perceptually plausible and human-recognizable human avatar in motion with detailed geometry and texture solely from a natural language prompt.

Humanoid robots are increasingly being developed for seamless interaction with humans in diverse domains, yet generating expressive and physically-feasible motions remains a core challenge. We propose a robust and automated pipeline for motion retargeting that enables the generation of natural, stable, and highly expressive motions for a wide variety of humanoid robots using different motion data sources, including noisy pose estimations. To ensure robustness, our approach unifies motions from different kinematic structures into a common canonical rig, systematically refines the motion trajectory to address infeasible poses, enforces foot-contact constraints, and enhances stability. The retargeted motion is then refined to closely follow the source motion while respecting each robot’s physical limits. Through extensive experiments on 12 simulated robots and validation on three real robots, we show that our methodology reliably produces expressive upper-body movements with consistent foot contact. This work represents an important step towards automating robust and expressive motion generation for humanoid robots, enabling deployment in various real-world scenarios.

Continuous-time score-based generative models consist of a pair of stochastic differential equations (SDEs)—a forward SDE that smoothly transitions data into a noise space and a reverse SDE that incrementally eliminates noise from a Gaussian prior distribution to generate data distribution samples—are intrinsically connected by the time-reversal theory on diffusion processes. In this paper, we investigate the use of stochastic evolution equations in Hilbert spaces, which expand the applicability of SDEs in two aspects: sample space and evolution operator, so they enable encompassing recent variations of diffusion models, such as generating functional data or replacing drift coefficients with image transformation. To this end, we derive a generalized time-reversal formula to build a bridge between probabilistic diffusion models and stochastic evolution equations and propose a score-based generative model called Hilbert Diffusion Model (HDM). Combining with Fourier neural operator, we verify the superiority of HDM for sampling functions from functional datasets with a power of kernel two-sample test of 4.2 on Quadratic, 0.2 on Melbourne, and 3.6 on Gridwatch, which outperforms existing diffusion models formulated in function spaces. Furthermore, the proposed method shows its strength in motion synthesis tasks by utilizing the Wiener process with values in Hilbert space. Finally, our empirical results on image datasets also validate a connection between HDM and diffusion models using heat dissipation, revealing the potential for exploring evolution operators and sample spaces.

Motion in-betweening (MIB) is a process of generating intermediate skeletal movement between the given start and target poses while preserving the naturalness of the motion, such as periodic footstep motion while walking. Although state-of-the-art MIB methods are capable of producing plausible motions given sparse key-poses, they often lack the controllability to generate motions satisfying the semantic contexts required in practical applications. We focus on the method that can handle pose or semantic conditioned MIB tasks using a unified model. We also present a motion augmentation method to improve the quality of pose-conditioned motion generation via defining a distribution over smooth trajectories. Our proposed method outperforms the existing state-of-the-art MIB method in pose prediction errors while providing additional controllability. Our code and results are available on our project web page: https://jihoonerd.github.io/Conditional-Motion-In-Betweening.