IEEE

Cross-Modal Guidance Network For Sketch-Based 3d Shape Retrieval

The main challenge of sketch-based 3D shape retrieval is the large cross-modal differences between 2D sketches and 3D shapes. Most recent works employed two heterogeneous networks and a shared loss to ...
GitHub

jtschwar/Multi-Modal-2D-Data-Fusion

1 Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI. 2 Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL. 3 Advanced Photon Source ...
IEEE

A Multi-Sensor Fusion Based 2D-Driven 3D Object Detection Approach for Large Scene Applications

Abstract: In this paper, we propose a 3D object detection approach for large-scale environments by considering the 2D visual information and 3D lidar data simultaneously. In the proposed multi-sensor ...
GitHub

Neural Feature Fusion Fields (N3F): 3D Distillation of Self-Supervised 2D Image Representations

This repository contains the official implementation of the paper Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations by Vadim Tschernezki, Iro Laina, Diane ...