4 papers
Neural Active Structure-from-Motion in Dark and Textureless Environment
Kazuto Ichimaru, Diego Thomas, Takafumi Iwaguchi +1
Active 3D measurement, especially structured light (SL) has been widely used in various fields for its robustness against textureless or equivalent surfaces by low light illuminati…
ActiveNeuS: Neural Signed Distance Fields for Active Stereo
Kazuto Ichimaru, Takaki Ikeda, Diego Thomas +2
3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of pote…
ACT2G: Attention-based Contrastive Learning for Text-to-Gesture Generation
Hitoshi Teshima, Naoki Wake, Diego Thomas +3
Recent increase of remote-work, online meeting and tele-operation task makes people find that gesture for avatars and communication robots is more important than we have thought. I…
Deep Gesture Generation for Social Robots Using Type-Specific Libraries
Hitoshi Teshima, Naoki Wake, Diego Thomas +3
Body language such as conversational gesture is a powerful way to ease communication. Conversational gestures do not only make a speech more lively but also contain semantic meanin…