2 papers
cs.CV2024
MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View
Emmanuelle Bourigault, Pauline Bourigault
Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into dif…
cs.LG2024
Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
Pauline Bourigault, Dongpo Xu, Danilo P. Mandic
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learn…