134 citations · 135 across the 15 of their papers we have counts for
5 papers · 1 filter
OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration
Pei An, Jiaqi Yang, Yulong Wang +2
Cross-attention is a crucial component in learning-based image-to-point-cloud (I2P) registration. Although existing cross-attention mechanisms have achieved promising progress, att…
Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration
Pei An, Muyao Peng, Junfeng Ding +2
Learning-based image-to-point-cloud (I2P) registration has garnered increasing attention in recent years. Nevertheless, existing methods still struggle with severe outliers under c…
RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation
Shiming Wang, Liangliang Nan, Julian Kooij +2
LiDAR scene flow estimates point-wise motion between two consecutive scans, referred to as the source and target. Leading self-supervised methods typically minimize the Chamfer los…
Efficient RWKV-based Representation Learning for 3D Point Clouds
Yun Liu, Xuefeng Yan, Liangliang Nan +5
The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling…
ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings
Xueyang Kang, Zijian Yu, Kourosh Khoshelham +1
Interactive segmentation allows efficient label generation by leveraging user-provided clicks to progressively refine predictions, which is critical when fully supervised labels ar…