research
∙
06/05/2023
Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data
Nowadays, robotics, AR, and 3D modeling applications attract considerabl...
share
research
∙
02/13/2023
Contour-based Interactive Segmentation
Recent advances in interactive segmentation (IS) allow speeding up and s...
research
∙
02/06/2023
Top-Down Beats Bottom-Up in 3D Instance Segmentation
Most 3D instance segmentation methods exploit a bottom-up strategy, typi...
research
∙
02/06/2023
TR3D: Towards Real-Time Indoor 3D Object Detection
Recently, sparse 3D convolutions have changed 3D object detection. Perfo...
research
∙
10/10/2022
Floorplan-Aware Camera Poses Refinement
Processing large indoor scenes is a challenging task, as scan registrati...
research
∙
12/01/2021
FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
Recently, promising applications in robotics and augmented reality have ...
research
∙
06/02/2021
ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
In this paper, we introduce the task of multi-view RGB-based 3D object d...
research
∙
09/25/2020
Towards General Purpose and Geometry Preserving Single-View Depth Estimation
Single-view depth estimation plays a crucial role in scene understanding...
research
∙
12/11/2019
Training Deep SLAM on Single Frames
Learning-based visual odometry and SLAM methods demonstrate a steady imp...
research
∙
10/10/2019
Measuring robustness of Visual SLAM
Simultaneous localization and mapping (SLAM) is an essential component o...
research
∙
09/26/2019
DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation
We present a novel dataset for training and benchmarking semantic SLAM m...
research
∙
07/16/2019