Search Results for author:
Found 2 papers, 1 papers with code
Spectrally Pruned Gaussian Fields with Neural Compensation
However, this comes with high memory consumption, e. g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory.
P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors
On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
