Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory

no code implementations • 26 May 2024 • Nikola Zubić, Federico Soldá, Aurelio Sulser, Davide Scaramuzza

Deep learning models have achieved significant success across various applications but continue to struggle with tasks requiring complex reasoning over sequences, such as function composition and compositional tasks.

State Space Models for Event Cameras

2 code implementations • 23 Feb 2024 • Nikola Zubić, Mathias Gehrig, Davide Scaramuzza

We address this challenge by introducing state-space models (SSMs) with learnable timescale parameters to event-based vision.

Event-based vision Object Detection

From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection

1 code implementation • ICCV 2023 • Nikola Zubić, Daniel Gehrig, Mathias Gehrig, Davide Scaramuzza

However, selecting the appropriate representation for the task traditionally requires training a neural network for each representation and selecting the best one based on the validation score, which is very time-consuming.

Event-based vision object-detection +3

An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering

1 code implementation • 5 Mar 2021 • Nikola Zubić, Pietro Liò

Then we use Poisson Surface Reconstruction to transform the reconstructed point cloud into a 3D mesh.

3D Reconstruction Pose Prediction +2