Picture for Charles R. Qi

Charles R. Qi

Stanford University

MoST: Multi-modality Scene Tokenization for Motion Prediction

Add code
Apr 30, 2024
Viaarxiv icon

Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving

Add code
Sep 25, 2023
Figure 1 for Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Figure 2 for Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Figure 3 for Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Figure 4 for Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Viaarxiv icon

MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences

Add code
Jun 05, 2023
Figure 1 for MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Figure 2 for MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Figure 3 for MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Figure 4 for MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Viaarxiv icon

WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting

Add code
Apr 07, 2023
Figure 1 for WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
Figure 2 for WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
Figure 3 for WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
Figure 4 for WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
Viaarxiv icon

GINA-3D: Learning to Generate Implicit Neural Assets in the Wild

Add code
Apr 04, 2023
Figure 1 for GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Figure 2 for GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Figure 3 for GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Figure 4 for GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Viaarxiv icon

NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors

Add code
Dec 06, 2022
Figure 1 for NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Figure 2 for NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Figure 3 for NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Figure 4 for NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Viaarxiv icon

Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining

Add code
Oct 15, 2022
Figure 1 for Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining
Figure 2 for Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining
Figure 3 for Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining
Viaarxiv icon

LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds

Add code
Oct 14, 2022
Figure 1 for LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
Figure 2 for LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
Figure 3 for LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
Figure 4 for LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
Viaarxiv icon

Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving

Add code
Oct 14, 2022
Figure 1 for Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Figure 2 for Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Figure 3 for Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Figure 4 for Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Viaarxiv icon

LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

Add code
Oct 10, 2022
Figure 1 for LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Figure 2 for LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Figure 3 for LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Figure 4 for LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Viaarxiv icon