no code implementations • 3 Feb 2024 • Hallison Paz, Tiago Novello, Luiz Velho
Our approach leverages the Fourier series by initializing the first layer of a sinusoidal neural network with integer frequencies with a period $P$.
1 code implementation • 26 Aug 2023 • Guilherme Schardong, Tiago Novello, Hallison Paz, Iurii Medvedev, Vinícius da Silva, Luiz Velho, Nuno Gonçalves
This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images.
no code implementations • 4 Dec 2022 • Tiago Novello
This work provides theoretical results to justify the compactness property of sinusoidal MLPs and provides control mechanisms in the definition and training of these networks.
no code implementations • 25 Aug 2022 • Hallison Paz, Tiago Novello, Vinicius Silva, Luiz Schirmer, Guilherme Schardong, Fabio Chagas, Helio Lopes, Luiz Velho
We present MR-Net, a general architecture for multiresolution neural networks, and a framework for imaging applications based on this architecture.
1 code implementation • ICCV 2023 • Tiago Novello, Vinicius da Silva, Guilherme Schardong, Luiz Schirmer, Helio Lopes, Luiz Velho
For this, it extends the representation of neural implicit surfaces to the space-time $\mathbb{R}^3\times \mathbb{R}$, which opens up mechanisms for continuous geometric transformations.
1 code implementation • 23 Jan 2022 • Tiago Novello, Guilherme Schardong, Luiz Schirmer, Vinicius da Silva, Helio Lopes, Luiz Velho
We introduce a neural implicit framework that exploits the differentiable properties of neural networks and the discrete geometry of point-sampled surfaces to approximate them as the level sets of neural implicit functions.
2 code implementations • 18 Dec 2020 • Vinícius da Silva, Tiago Novello, Hélio Lopes, Luiz Velho
We introduce Proceduray, an engine for real-time ray tracing of procedural geometry.
Graphics 68U05 (Primary) 37-04, 37F10 (Secondary) I.3.7