Search Results for author:
Found 9 papers, 6 papers with code
PillarTrack: Redesigning Pillar-based Transformer Network for Single Object Tracking on Point Clouds
LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving.
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process.
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup.
RobustCalib: Robust Lidar-Camera Extrinsic Calibration with Consistency Learning
Current traditional methods for LiDAR-camera extrinsics estimation depend on offline targets and human efforts, while learning-based approaches resort to iterative refinement for calibration results, posing constraints on their generalization and application in on-board systems.
FastPillars: A Deployment-friendly Pillar-based 3D Detector
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
Real-time 3D Single Object Tracking with Transformer
PTT module in the voting stage could model the interactions among point patches, which learns context-dependent features.
3D Object Tracking with Transformer
By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient.
PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds
Our code is open-sourced for the robotics community at https://github. com/shanjiayao/PTT.
3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud
Then, to fuse the information of features in the two branches and obtain their similarity, we propose two cross correlation modules, named Pointcloud-wise and Point-wise respectively.
