SE(2)-Constrained Visual Inertial Fusion for Ground Vehicles
PulseAugur coverage of SE(2)-Constrained Visual Inertial Fusion for Ground Vehicles — every cluster mentioning SE(2)-Constrained Visual Inertial Fusion for Ground Vehicles across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
FreeOcc model efficiently forecasts 4D occupancy by decoupling ego-motion
Researchers have developed FreeOcc, a novel 4D occupancy forecasting model that efficiently disentangles ego-motion from scene dynamics. This model utilizes a continuous-time framework with explicit SE(2) geometric deco…
-
New SE(2)-Invariant Networks Offer Optimal Efficiency for Neural Architectures
Researchers have developed a new method to integrate known data symmetries into neural network architectures, specifically focusing on SE(2) invariance which accounts for both translations and rotations. This approach u…
-
New neural network framework learns complex Lie-Poisson system dynamics
Researchers have developed Latent Lie-Poisson Neural Networks (LLPNNs), a novel framework designed to learn and predict the dynamics of Lie-Poisson systems directly from observable data. These systems are crucial for mo…
-
New Lie-Algebra Attention Treats Tokens as Group Elements
Researchers have introduced a novel attention mechanism called Lie-Algebra Attention, which treats tokens as elements of a matrix Lie group. This approach allows attention scores to be derived from the intrinsic geometr…
-
New framework models video dynamics as group actions
Researchers have proposed a new framework for understanding video world models by framing their dynamics as group actions. This approach focuses on the compositional structure of actions, particularly in embodied settin…