Browse > Computer Vision > Object Recognition > 3D Object Recognition

3D Object Recognition

10 papers with code ยท Computer Vision
Subtask of Object Recognition

3D object recognition is the task of recognising objects from 3D data.

State-of-the-art leaderboards

Latest papers without code

Task-Aware Monocular Depth Estimation for 3D Object Detection

17 Sep 2019

In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.

3D OBJECT DETECTION 3D OBJECT RECOGNITION MONOCULAR DEPTH ESTIMATION

Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition

26 Jul 2019

In this work, each object is represented using a set of general latent visual topics and category-specific dictionaries.

3D OBJECT RECOGNITION OBJECT CLASSIFICATION

SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation

25 Jul 2019

In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.

3D OBJECT RECOGNITION SCENE GENERATION

Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images

22 Jul 2019

Finally, we propose the best cluster numbers for each class of objects in KITTI dataset that improves the performance of detection model significantly.

3D OBJECT RECOGNITION AUTONOMOUS DRIVING

Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects

15 Jul 2019

In this paper, we therefore propose a loss to specifically address the hubness problem.

3D OBJECT RECOGNITION GENERALIZED ZERO-SHOT LEARNING

A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching

5 Jul 2019

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision.

3D OBJECT RECOGNITION POINT CLOUD REGISTRATION

MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks

15 Jun 2019

Experimental results on ModelNet10 and ModelNet40 datasets show that our MV-C3D technique can achieve outstanding performance with multi-view images which are captured from partial angles with less range.

3D OBJECT RECOGNITION

Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images

3 Jun 2019

Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars.

3D OBJECT RECOGNITION SELF-DRIVING CARS SIMULTANEOUS LOCALIZATION AND MAPPING

Volumetric Convolution: Automatic Representation Learning in Unit Ball

ICLR 2019

Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks.

3D OBJECT RECOGNITION 3D SHAPE ANALYSIS REPRESENTATION LEARNING