7 papers
Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting
Felipe Nunes Carbone de Carvalho, Joyce de Morais Souza, Alan de Aguiar +2
Domain Randomization (DR) is a standard technique for closing the Sim-to-Real gap, yet traditional DR pipelines rely on classical computer graphics rendering driven by polygon mesh…
Toward Inclusive Avatar Design with Limb Differences Through Artificial Intelligence
Fernanda Miyuki Yamada, João Paulo Gois, Hiroki Takahashi
As extended reality becomes more popular for social interaction and entertainment, 3D avatars must represent the full diversity of body types. Most 3D avatar systems only support n…
Topo-GS: Continuous Volumetric Embedding of High-Dimensional Data via Topological Gaussian Splatting
João Paulo Gois, Luis Gustavo Nonato
Dimensionality reduction algorithms map high-dimensional data into visualizable 2D or 3D spaces, but traditionally rely on a discrete point-cloud paradigm. This discrete abstractio…
The Rise of AI-Generated Anime Avatars: Trends, Challenges, and Opportunities
Fernanda Miyuki Yamada, João Paulo Gois, Hiroki Takahashi
The rise of 3D anime-style avatars in gaming, virtual reality, and other digital media has driven significant interest in automated generation methods capable of capturing their di…
HideAndSeg: an AI-based tool with automated prompting for octopus segmentation in natural habitats
Alan de Aguiar, Michaella Pereira Andrade, Charles Morphy D. Santos +1
Analyzing octopuses in their natural habitats is challenging due to their camouflage capability, rapid changes in skin texture and color, non-rigid body deformations, and frequent…
Reproducibility and scientific interpretation in the age of AI: consilience in biological systematics, ecology, and molecular biology
Charles Morphy D. Santos, Luciana Campos Paulino, Michaella P. Andrade +2
Achieving complete reproducibility in science, particularly in research fields such as biodiversity, is challenging due to analytical choices, bias and interpretation. Here, we exa…
FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation
Manolo Canales Cuba, Vinícius do Carmo Melício, João Paulo Gois
Achieving high-fidelity and temporally smooth 3D human motion generation remains a challenge, particularly within resource-constrained environments. We introduce FlowMotion, a nove…