Bruno Roy

Marco Pegoraro, Evan Atherton, Bruno Roy et al.

Learning natural body motion remains challenging due to the strong coupling between spatial geometry and temporal dynamics. Embedding motion in phase manifolds, latent spaces that capture local periodicity, has proven effective for motion prediction; however, existing approaches lack scalability and remain confined to specific settings. We introduce FunPhase, a functional periodic autoencoder that learns a phase manifold for motion and replaces discrete temporal decoding with a function-space formulation, enabling smooth trajectories that can be sampled at arbitrary temporal resolutions. FunPhase supports downstream tasks such as super-resolution and partial-body motion completion, generalizes across skeletons and datasets, and unifies motion prediction and generation within a single interpretable manifold. Our model achieves substantially lower reconstruction error than prior periodic autoencoder baselines while enabling a broader range of applications and performing on par with state-of-the-art motion generation methods.

Bruno Roy

Partitioning a polygonal mesh into meaningful parts can be challenging. Many applications require decomposing such structures for further processing in computer graphics. In the last decade, several methods were proposed to tackle this problem, at the cost of intensive computational times. Recently, machine learning has proven to be effective for the segmentation task on 3D structures. Nevertheless, these state-of-the-art methods are often hardly generalizable and require dividing the learned model into several specific classes of objects to avoid overfitting. We present a data-driven approach leveraging deep learning to encode a mapping function prior to mesh segmentation for multiple applications. Our network reproduces a neighborhood map using our knowledge of the \textsl{Shape Diameter Function} (SDF) method using similarities among vertex neighborhoods. Our approach is resolution-agnostic as we downsample the input meshes and query the full-resolution structure solely for neighborhood contributions. Using our predicted SDF values, we can inject the resulting structure into a graph-cut algorithm to generate an efficient and robust mesh segmentation while considerably reducing the required computation times.

AmirHossein Zamani, Bruno Roy, Arianna Rampini

Recent 3D generative models produce high-quality textures for 3D mesh objects. However, they commonly rely on the heavy assumption that input 3D meshes are accompanied by manual mesh parameterization (UV mapping), a manual task that requires both technical precision and artistic judgment. Industry surveys show that this process often accounts for a significant share of asset creation, creating a major bottleneck for 3D content creators. Moreover, existing automatic methods often ignore two perceptually important criteria: (1) semantic awareness (UV charts should align semantically similar 3D parts across shapes) and (2) visibility awareness (cutting seams should lie in regions unlikely to be seen). To overcome these shortcomings and to automate the mesh parameterization process, we present an unsupervised differentiable framework that augments standard geometry-preserving UV learning with semantic- and visibility-aware objectives. For semantic-awareness, our pipeline (i) segments the mesh into semantic 3D parts, (ii) applies an unsupervised learned per-part UV-parameterization backbone, and (iii) aggregates per-part charts into a unified UV atlas. For visibility-awareness, we use ambient occlusion (AO) as an exposure proxy and back-propagate a soft differentiable AO-weighted seam objective to steer cutting seams toward occluded regions. By conducting qualitative and quantitative evaluations against state-of-the-art methods, we show that the proposed method produces UV atlases that better support texture generation and reduce perceptible seam artifacts compared to recent baselines. Our implementation code is publicly available at: https://github.com/AHHHZ975/Semantic-Visibility-UV-Param.

Aliasghar Khani, Arianna Rampini, Bruno Roy et al.

Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual agents to human-robot interaction. As the field has rapidly progressed with the introduction of diverse modeling paradigms including GANs, autoencoders, autoregressive models, and diffusion-based techniques, each approach brings its own advantages and limitations. This growing diversity has created a need for a comprehensive and structured review that specifically examines recent developments from the perspective of the generative approach employed. In this survey, we provide an in-depth categorization of motion generation methods based on their underlying generative strategies. Our main focus is on papers published in top-tier venues since 2023, reflecting the most recent advancements in the field. In addition, we analyze architectural principles, conditioning mechanisms, and generation settings, and compile a detailed overview of the evaluation metrics and datasets used across the literature. Our objective is to enable clearer comparisons and identify open challenges, thereby offering a timely and foundational reference for researchers and practitioners navigating the rapidly evolving landscape of motion generation.

Aliasghar Khani, Arianna Rampini, Evan Atherton et al.

Motion generation is a cornerstone of computer graphics, animation, gaming, and robotics, enabling the creation of realistic and varied character movements. A significant limitation of existing methods is their reliance on specific skeletal structures, which restricts their versatility across different characters. To overcome this, we introduce UniMoGen, a novel UNet-based diffusion model designed for skeleton-agnostic motion generation. UniMoGen can be trained on motion data from diverse characters, such as humans and animals, without the need for a predefined maximum number of joints. By dynamically processing only the necessary joints for each character, our model achieves both skeleton agnosticism and computational efficiency. Key features of UniMoGen include controllability via style and trajectory inputs, and the ability to continue motions from past frames. We demonstrate UniMoGen's effectiveness on the 100style dataset, where it outperforms state-of-the-art methods in diverse character motion generation. Furthermore, when trained on both the 100style and LAFAN1 datasets, which use different skeletons, UniMoGen achieves high performance and improved efficiency across both skeletons. These results highlight UniMoGen's potential to advance motion generation by providing a flexible, efficient, and controllable solution for a wide range of character animations.

Arianna Rampini, Kanika Madan, Bruno Roy et al.

High-quality textures are critical for realistic 3D content creation, yet existing generative methods are slow, rely on UV maps, and often fail to remain faithful to a reference image. To address these challenges, we propose a transformer-based framework that predicts a 3D texture field directly from a single image and a mesh, eliminating the need for UV mapping and differentiable rendering, and enabling faster texture generation. Our method integrates a triplane representation with depth-based backprojection losses, enabling efficient training and faster inference. Once trained, it generates high-fidelity textures in a single forward pass, requiring only 0.2s per shape. Extensive qualitative, quantitative, and user preference evaluations demonstrate that our method outperforms state-of-the-art baselines on single-image texture reconstruction in terms of both fidelity to the input image and perceptual quality, highlighting its practicality for scalable, high-quality, and controllable 3D content creation.

Bruno Roy

In this work, we introduce FluidsFormer: a transformer-based approach for fluid interpolation within a continuous-time framework. By combining the capabilities of PITT and a residual neural network (RNN), we analytically predict the physical properties of the fluid state. This enables us to interpolate substep frames between simulated keyframes, enhancing the temporal smoothness and sharpness of animations. We demonstrate promising results for smoke interpolation and conduct initial experiments on liquids.

Bruno Roy, Pierre Poulin, Eric Paquette

We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks. Our approach infers and synthesizes small- and large-scale details solely from a low-resolution particle-based liquid simulation. The proposed network leverages neighborhood contributions to encode inherent liquid properties throughout convolutions. We also propose a particle-based approach to interpolate between liquids generated from varying simulation discretizations using a state-of-the-art bidirectional optical flow solver method for fluids in addition to a novel key-event topological alignment constraint. In conjunction with the neighborhood contributions, our loss formulation allows the inference model throughout epochs to reward important differences in regard to significant gaps in simulation discretizations. Even when applied in an untested simulation setup, our approach is able to generate plausible high-resolution details. Using this interpolation approach and the predicted displacements, our approach combines the input liquid properties with the predicted motion to infer semi-Lagrangian advection. We furthermore showcase how the proposed interpolation approach can facilitate generating large simulation datasets with a subset of initial condition parameters.

Antoine Proulx, Francis Raymond, Bruno Roy et al.

Context: The software industry needs to adapt itself to a rapidly changing market. Continuous practices (Continuous Integration, Continuous Delivery and Continuous Deployment), commonly found in Agile development processes, it is possible to deliver new features more frequently to clients, integrating of smaller features is less likely to cause conflicts than the more traditional approach of merging big features less frequently all at once. However, Continuous Deployment is no clear way on the best approaches for their implementation. Objective: The goal of this paper is to identify the challenges and the solutions related to Continuous Deployment, and then see which of those solutions can be applied to which challenges. Method: This paper is a systematic literature review of the problems and the solutions found when implementing the continuous deployment practice inside an organization. It also presents which solution can be applied to which problem. Thirty-one articles published after 2015 were analyzed for this SLR. Results: 22 problems were grouped inside the categories Human and Organizational, Process, Tools, Infrastructure, Application Architecture and Testing. The 19 solutions found were grouped inside the categories Human and Organizational, Architecture, Process and Tools. Solutions have been found for 14 problems and some questions have been identified for future research. Conclusion: this article is to serve as a reference for the practitioner who wants to find how to solve a specific challenge when implementing the continuous deployment practice.