FALO achieves competitive accuracy on nuScenes and Waymo LiDAR benchmarks while running 1.6-9.8x faster than prior state-of-the-art methods on mobile GPUs and NPUs through a hardware-friendly voxel sequencing and ConvDotMix architecture.
Fsd v2: Improving fully sparse 3d object detection with virtual voxels
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Automatically constructed mapping priors from sensor aggregation are integrated via the MPA3D framework to achieve state-of-the-art 3D detection results on the Waymo Open Dataset.
citing papers explorer
-
FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices
FALO achieves competitive accuracy on nuScenes and Waymo LiDAR benchmarks while running 1.6-9.8x faster than prior state-of-the-art methods on mobile GPUs and NPUs through a hardware-friendly voxel sequencing and ConvDotMix architecture.
-
Scene Reconstruction as Mapping Priors for 3D Detection
Automatically constructed mapping priors from sensor aggregation are integrated via the MPA3D framework to achieve state-of-the-art 3D detection results on the Waymo Open Dataset.