Presentation / Installation
OctFormer: Octree-based Transformers for 3D Point Clouds
SessionDeep Geometric Learning
DescriptionOctFormer is a general, effective, and scalable backbone for 3D point cloud learning. Octformer leverages a novel octree attention that partitions point clouds into irregular local windows containing a fixed number of points. OctFormer achieves state-of-the-art performances on 3D segmentation on ScanNet/ScanNet200 and 3D detection on SUN RGB-D.
Event Type
Technical Paper
TimeThursday, 10 August 20232pm - 2:11pm PDT
LocationRoom 515 A
ACM Digital Library
Technical Papers pdfs
Session Time & Location
Research & Education
Livestreamed
Recorded
Modeling
Rendering
FC
FCS
V
VS
EFC