9 papers
FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
Marco Pegoraro, Evan Atherton, Bruno Roy +2
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…
Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives
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 me…
3D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapes
Tejaswini Medi, Arianna Rampini, Pradyumna Reddy +2
Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike…
Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details
Tejaswini Medi, Hsien-Yi Wang, Arianna Rampini +1
Latent generative models compress images into learned embeddings prior to synthesis, and the generation quality critically depends on how faithfully these embeddings preserve visua…
A Scalable Attention-Based Approach for Image-to-3D Texture Mapping
Arianna Rampini, Kanika Madan, Bruno Roy +2
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 im…
Motion Generation: A Survey of Generative Approaches and Benchmarks
Aliasghar Khani, Arianna Rampini, Bruno Roy +5
Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and rob…