Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondence

Vencia Herzog, Stefan Suwelack
10/12/2024
cs.CVcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Self-supervised pre-training has achieved remarkable success in NLP and 2D vision. However, these advances have yet to translate to 3D data. Techniques like masked reconstruction face inherent challenges on unstructured point clouds, while many contrastive learning tasks lack in complexity and informative value. In this paper, we present Pic@Point, an effective contrastive learning method based on structural 2D-3D correspondences. We leverage image cues rich in semantic and contextual knowledge to provide a guiding signal for point cloud representations at various abstraction levels. Our lightweight approach outperforms state-of-the-art pre-training methods on several 3D benchmarks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images

89% match2024

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning

88% match1 repo102024

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-Training

87% match1 repo352026

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

87% match1 repo3.0k2026

To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning

85% match2026

FAC: 3D Representation Learning via Foreground Aware Feature Contrast

85% match1 repo422026

Cite this paper

@article{herzog2024picpoint,
  title  = {Pic@Point: Cross-Modal Learning by Local and Global Point-Picture Correspondence},
  author = {Vencia Herzog and Stefan Suwelack},
  year   = {2024},
  eprint = {2410.09519},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.09519v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.09519.svg)](https://codeofpaper.com/paper/2410.09519)

Discussion