-
TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network [Abstract]
-
Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects [Abstract]
-
Real-Time Video Inpainting for RGB-D Pipeline Reconstruction [Abstract]
-
Mufeat: Multi-Level Cnn and Unsupervised Learning for Local Feature Detection and Description [Abstract]
-
Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition [Abstract]
-
TransTouch: Learning Transparent Objects Depth Sensing through Sparse Touches [Abstract]
-
WatchPed: Pedestrian Crossing Intention Prediction Using Embedded Sensors of Smartwatch [Abstract]
-
Object Detection Based on Raw Bayer Images [Abstract]
-
SDFMAP: Neural Signed Distance Fields for Mapping and Positioning in Real-Time [Abstract]
-
LocalViT: Analyzing Locality in Vision Transformers [Abstract]
-
CLONeR: Camera-Lidar Fusion for Occupancy Grid-Aided Neural Representations [Abstract]
-
Certifiable Object Pose Estimation: Foundations, Learning Models, and Self-Training [Abstract]
-
Perspective Aware Road Obstacle Detection [Abstract]