A direct feature-space approach for 3D LiDAR anomaly segmentation achieves competitive results on existing and new mixed real-synthetic datasets.
Dynamic graph cnn for learning on point clouds.ACM TOG, 38(5): 1–12
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DEC combines a DINO backbone, a Chunking and Adapting Module, and CLIP-driven virtual feature synthesis to improve open-set 3D object retrieval on standard benchmarks.
citing papers explorer
-
Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation
A direct feature-space approach for 3D LiDAR anomaly segmentation achieves competitive results on existing and new mixed real-synthetic datasets.
-
DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval
DEC combines a DINO backbone, a Chunking and Adapting Module, and CLIP-driven virtual feature synthesis to improve open-set 3D object retrieval on standard benchmarks.