Cross-modal Learning for Image-Guided Point Cloud Shape Completion
Nov 28, 2022
Speakers
Emanuele Aiello
Speaker · 0 followers
Diego Valsesia
Speaker · 0 followers
Enrico Magli
Speaker · 0 followers
About
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 self-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 self-supervised approach which outperforms a number of supervised methods and is competitive with the latest supervised models only exploiting point cloud information.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 self-supervised setting where the auxiliary image provides a supervisory signal to the training process by using a differentiable render…
Organizer
NeurIPS 2022
Account · 954 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Featured Papers Panels 6B
Watch later
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%
Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Elicitation Inference Optimization for Multi-Principal-Agent Alignment
Watch later
Andrew Konya, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning to Attack Federated Learning: A Model-based Reinforcement Learning Attack Framework
Watch later
Henger Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Understanding stock market instability via graph auto-encoders
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Inception Transformer
Watch later
Chenyang Si, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%