DeepAI AI Chat
Log In Sign Up

Cross-modal Learning for Image-Guided Point Cloud Shape Completion

by   Emanuele Aiello, et al.
Politecnico di Torino

In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two modalities in a localized latent space, thus avoiding the need for complex point cloud reconstruction methods from single views used by the state-of-the-art. We also investigate a novel weakly-supervised setting where the auxiliary image provides a supervisory signal to the training process by using a differentiable renderer on the completed point cloud to measure fidelity in the image space. Experiments show significant improvements over state-of-the-art supervised methods for both unimodal and multimodal completion. We also show the effectiveness of the weakly-supervised approach which outperforms a number of supervised methods and is competitive with the latest supervised models only exploiting point cloud information.


View-Guided Point Cloud Completion

This paper presents a view-guided solution for the task of point cloud c...

Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels

Point cloud analysis has received much attention recently; and segmentat...

PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding

Some self-supervised cross-modal learning approaches have recently demon...

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Weakly supervised point cloud segmentation, i.e. semantically segmenting...

RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion

We present RL-GAN-Net, where a reinforcement learning (RL) agent provide...

Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

Although recent point cloud analysis achieves impressive progress, the p...

Graph-Guided Deformation for Point Cloud Completion

For a long time, the point cloud completion task has been regarded as a ...

Code Repositories


Code for "Cross-modal Learning for Image-Guided Point Cloud Shape Completion" (NeurIPS 2022)

view repo