134 citations · 135 across the 15 of their papers we have counts for
17 papers
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…
I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs
Yu Qi, Lipeng Gu, Honghua Chen +2
Existing 3D visual grounding methods rely on precise text prompts to locate objects within 3D scenes. Speech, as a natural and intuitive modality, offers a promising alternative. R…
Unified Representation Space for 3D Visual Grounding
Yinuo Zheng, Lipeng Gu, Honghua Chen +2
3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separa…
PointSFDA: Source-free Domain Adaptation for Point Cloud Completion
Xing He, Zhe Zhu, Liangliang Nan +3
Conventional methods for point cloud completion, typically trained on synthetic datasets, face significant challenges when applied to out-of-distribution real-world scans. In this…
CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction
Lipeng Gu, Xuefeng Yan, Weiming Wang +4
The fusion of camera- and LiDAR-based detections offers a promising solution to mitigate tracking failures in 3D multi-object tracking (MOT). However, existing methods predominantl…
PointCG: Self-supervised Point Cloud Learning via Joint Completion and Generation
Yun Liu, Peng Li, Xuefeng Yan +6
The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects…
First Mapping the Canopy Height of Primeval Forests in the Tallest Tree Area of Asia
Guangpeng Fan, Fei Yan, Xiangquan Zeng +8
We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community wor…
On the Estimation of Image-matching Uncertainty in Visual Place Recognition
Mubariz Zaffar, Liangliang Nan, Julian F. P. Kooij
In Visual Place Recognition (VPR) the pose of a query image is estimated by comparing the image to a map of reference images with known reference poses. As is typical for image ret…
PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis
Lipeng Gu, Xuefeng Yan, Liangliang Nan +4
Current methodologies in point cloud analysis predominantly explore 3D geometries, often achieved through the introduction of intricate learnable geometric extractors in the encode…
MuVieCAST: Multi-View Consistent Artistic Style Transfer
Nail Ibrahimli, Julian F. P. Kooij, Liangliang Nan
We introduce MuVieCAST, a modular multi-view consistent style transfer network architecture that enables consistent style transfer between multiple viewpoints of the same scene. Th…
Cross-BERT for Point Cloud Pretraining
Xin Li, Peng Li, Zeyong Wei +7
Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be ad…
UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities
Shiming Wang, Holger Caesar, Liangliang Nan +1
Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., d…
City3D: Large-Scale Building Reconstruction from Airborne LiDAR Point Clouds
Jin Huang, Jantien Stoter, Ravi Peters +1
We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne…