2 citations · 2 across the 5 of their papers we have counts for
6 papers
Tri-Efficient Transfer Learning for Point Cloud Videos
Yiding Sun, Dongxu Zhang, Jihua Zhu +6
While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two criti…
Diffusion Masked Pretraining for Dynamic Point Cloud
Zhuoyue Zhang, Jihua Zhu, Yiding Sun +4
Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth…
PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
Dongxu Zhang, Yiding Sun, Pengcheng Li +12
While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…
NVAutoNet: Fast and Accurate 360 3D Visual Perception For Self Driving
Trung Pham, Mehran Maghoumi, Wanli Jiang +9
Achieving robust and real-time 3D perception is fundamental for autonomous vehicles. While most existing 3D perception methods prioritize detection accuracy, they often overlook cr…
PillarFlow: End-to-end Birds-eye-view Flow Estimation for Autonomous Driving
Kuan-Hui Lee, Matthew Kliemann, Adrien Gaidon +4
In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particula…
Real-Time Panoptic Segmentation from Dense Detections
Rui Hou, Jie Li, Arjun Bhargava +5
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot…