Occ-ScanNet
PulseAugur coverage of Occ-ScanNet — every cluster mentioning Occ-ScanNet across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AdaOcc method advances 3D occupancy prediction for embodied AI tasks
Researchers have developed AdaOcc, a novel point-based method for adaptive 3D semantic occupancy prediction designed for embodied AI tasks. This approach can flexibly adjust its computational budget by varying the numbe…
-
New OccAnyScene framework unifies indoor-outdoor 3D occupancy prediction
Researchers have introduced OccAnyScene, a novel framework designed for unified 3D occupancy prediction across both indoor and outdoor environments. This new approach addresses the challenge of handling diverse scenes w…
-
YouTube-Occ learns 3D semantic occupancy from web videos
Researchers have developed YouTube-Occ, a novel method for predicting 3D semantic occupancy from internet videos, addressing the scarcity of annotated 3D indoor data. The system utilizes a pipeline that processes raw we…
-
VEOcc framework advances online 3D occupancy prediction
Researchers have introduced VEOcc, a novel voxel-centric framework designed for online 3D occupancy prediction and mapping. This system incrementally builds dense spatial representations on the fly, overcoming limitatio…
-
HKUST(GZ) unveils LegoOcc for single-image 3D indoor space understanding
Researchers from Hong Kong University of Science and Technology (Guangzhou) have developed LegoOcc, a novel system capable of predicting 3D occupancy in indoor scenes using only a single RGB image. This method bypasses …