arXiv subjects

Dhruv Agrawal

Publications and source records attributed to Dhruv Agrawal.

6 recordsLinked to original sources

arXiv2026

Interactive Generative Motion Editing via Scheduled Inpainting

Motion editing is central to VFX and game development, where it is used extensively to modify and augment existing movements to conform to new environments or changes in artistic direction. While traditional motion editing can do small modifications, it cannot accommodate larger structural edits, resulting in visual warping artifacts that require authoring new motion. Conversely, recent advances in large-scale generative modeling have unlocked newfound capabilities for authoring entire movements by directly manipulating sparse spatial constraints. While impressive at creating new movements, these methods lack the capability to preserve and edit existing motion interactively. In this work, we introduce scheduled inpainting, a method that enables interactive generative motion editing, a novel paradigm unifying motion synthesis and editing by leveraging generative models. Scheduled inpainting is a simple yet powerful inference-based technique that enables fine-grained spatiotemporal control over the balance between preserving the original motion and generating new content. By building atop generative models that support direct manipulation, our system allows artists to interactively refine existing animations while ensuring results remain natural and consistent with the learned motion distribution. Scheduled inpainting is versatile and supports many editing applications, such as extending, stitching, and compositing different clips. Finally, we extensively validate our approach by comparing with four baselines, conducting ablations of our design, and reporting user feedback.

cs.GR↗

arXiv2026

Two2Four: Generative Quadruped Puppeteering from Human Motion

Realistic animal motion for virtual production is typically obtained either through motion capture of highly trained performers who accurately mimic animal behavior, or by retargeting ordinary human motion using complex control setups. Both approaches are challenging and often fail to fully reproduce the nuances of natural animal motion, motivating data-driven alternatives. We present an automatic human-to-quadruped puppeteering framework that produces plausible and controllable quadruped motions from ordinary human motion data. Our approach employs a two-stage generative diffusion model trained purely on quadruped motion data. By introducing a structured conditioning and inpainting strategy, our method supports a wide range of actions, including walking, running, jumping, sitting, and lying. Furthermore, we enable fine-grained intuitive control of the quadruped motion such as head movement control and individual limb puppeteering. Experimental results demonstrate improved motion realism and controllability compared to existing retargeting approaches, highlighting the effectiveness of our framework as a tool for animation and virtual production applications.

cs.GR↗

arXiv2026

Conditional Residence Times and Sequential Transition Dynamics of an Overdamped Dimer

We investigate the completion dynamics of an overdamped dimer moving in a bistable potential under thermal fluctuations and a weak periodic force. Both monomers start in one of the two wells separated by a barrier. The transition is initiated when the monomer closer to the barrier makes a jump across it. The completion dynamics refers to the next part of the dynamics where the second monomer has to wait for some time before it can follow up. We use the Conditional Residence Time (CRT) to study the delay between the successive barrier crossing of the two monomers. The CRT distributions highlight qualitatively different regimes formed by the competition between the escape times of the lagging monomer and the time period of the external drive. The effect is strongest in the weak coupling regime where the delayed completion is spread across multiple forcing cycles. By partitioning this process into three windows, i.e. the immediate, first cycle and later cycles, we show that the probability that the lagging monomer will make a transition in the said cycle is redistributed among these pathways as we change the frequency of the drive. This leads to a non-monotonic dependence of the mean CRT on the frequency of the drive. Our results demonstrate that transition initiation and completion in a coupled system are two separate processes and establish CRT as a useful measure to quantify the sequential barrier crossing dynamics in coupled stochastic systems.

cond-mat.stat-mech↗

arXiv2026

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion data to facilitate style transfer. Our approach is guided by the insight that content corresponds to coarse motion attributes while style captures the finer, expressive details. To model this hierarchy, we employ Residual Vector Quantized Variational Autoencoders (RVQ-VAEs) to learn a coarse-to-fine representation of motion. We further enhance the disentanglement by integrating codebook learning with contrastive learning and a novel information leakage loss to organize the content and the style across different codebooks. We harness this disentangled representation using our simple and effective inference-time technique Quantized Code Swapping, which enables motion style transfer without requiring any fine-tuning for unseen styles. Our framework demonstrates strong versatility across multiple inference applications, including style transfer, style removal, and motion blending.

cs.CV↗

arXiv2025

DQ-NMPC: Dual-Quaternion NMPC for Quadrotor Flight

MAVs have great potential to assist humans in complex tasks, with applications ranging from logistics to emergency response. Their agility makes them ideal for operations in complex and dynamic environments. However, achieving precise control in agile flights remains a significant challenge, particularly due to the underactuated nature of quadrotors and the strong coupling between their translational and rotational dynamics. In this work, we propose a novel NMPC framework based on dual-quaternions (DQ-NMPC) for quadrotor flight. By representing both quadrotor dynamics and the pose error directly on the dual-quaternion manifold, our approach enables a compact and globally non-singular formulation that captures the quadrotor coupled dynamics. We validate our approach through simulations and real-world experiments, demonstrating better numerical conditioning and significantly improved tracking performance, with reductions in position and orientation errors of up to 56.11% and 56.77%, compared to a conventional baseline NMPC method. Furthermore, our controller successfully handles aggressive trajectories, reaching maximum speeds up to 13.66 m/s and accelerations reaching 4.2 g within confined space conditions of dimensions 11m x 4.5m x 3.65m under which the baseline controller fails.

cs.RO↗

arXiv2024

Coupling-Induced Synchronized Motion and Stochastic Resonance in Overdamped Dimers

In this study, we explore an overdamped system of a dimer in a bistable potential immersed in a heat bath. The monomers interact via the combination of the Lennard-Jones potential and the harmonic potential. We have introduced a short-range interaction in our model making it more physical. Such a classical system can be used as a model for stochastic resonance (SR) based energy harvesters where the interplay between the noise, coupling and a periodic perturbation leads to a rich class of dynamical behaviours. A key distinction between observing SR in single and coupled particle studies is that a transition between the two wells is only considered successful if both the particles cross a certain threshold position. Although we observe qualitatively a similar peaking behaviour in different quantifiers of SR (like input energy ($W_p$) and hysteresis loop area (HLA)), the effects of the above-mentioned condition on the dynamics of the system remain unaddressed to the best of our knowledge. We study SR using different measures like the input energy per period of the external forcing, the hysteresis loop area as well as quantities like phase lag between the response and the external forcing and the maximum average amplitude of the response. Additionally, we have defined a new quantity called the successful transition ratio. This ratio helps us understand the effects of the dimer's coupling on the number of successful transitions out of the total attempted transitions. The successful transition ratio is almost unity for strongly coupled dimer suggesting most of the transition attempts end up successfully however few they are in numbers. On the other hand, the ratio shows a peaking behaviour with respect to noise for weak and intermediate couplings. We show that only for the weakly coupled dimer, the ratio is maximum around the temperature where SR takes place.

cond-mat.stat-mech↗