RLSplat makes feed-forward Gaussian splatting scale with the budget
Latency and peak memory fall with the Gaussian budget, unlike prune-after-dense methods that stay nearly constant.
4 stories, newest first · one card per story
Latency and peak memory fall with the Gaussian budget, unlike prune-after-dense methods that stay nearly constant.
View-wise and 3D grouping plus rendering-error feedback keep Gaussian counts at or below prior methods.
InfiniSplat v2 improves feed-forward 3D Gaussian rendering quality across large viewpoint changes.
FAMOS is a feed-forward model predicting movable-part segmentation and joint parameters from sparse unordered point clouds, beating baselines on PartNet-Mobility, ACD, and ArtiCraft-10K.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views