BMLiCap models motion with Bézier curves and multi-scale transformers to achieve state-of-the-art LiDAR-based human pose capture on four benchmarks.
Robust single-stage fully sparse 3d object detection via detachable latent diffusion
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
GEM is a new LiDAR world model using deformable Mamba that disentangles dynamic and static features to generate high-fidelity simulations and achieve state-of-the-art results on autonomous driving benchmarks.
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
citing papers explorer
-
B\'ezier Degradation Modeling for LiDAR-based Human Motion Capture
BMLiCap models motion with Bézier curves and multi-scale transformers to achieve state-of-the-art LiDAR-based human pose capture on four benchmarks.
-
GEM: Generating LiDAR World Model via Deformable Mamba
GEM is a new LiDAR world model using deformable Mamba that disentangles dynamic and static features to generate high-fidelity simulations and achieve state-of-the-art results on autonomous driving benchmarks.
-
Deep Image Clustering Based on Curriculum Learning and Density Information
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.