FI3Det leverages VLMs to enable few-shot incremental 3D detection of novel objects, reporting consistent gains over baselines on ScanNet V2 and SUN RGB-D under batch and sequential settings.
AIC3DOD: Advancing Indoor Class- Incremental 3D Object Detection with Point Transformer Architecture and Room Layout Constraints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments
FI3Det leverages VLMs to enable few-shot incremental 3D detection of novel objects, reporting consistent gains over baselines on ScanNet V2 and SUN RGB-D under batch and sequential settings.