A Cookbook of 3D Vision: Data, Learning Paradigms, and Application
Quick Answer
This article presents a data-centric taxonomy of 3D vision, linking geometric representations like point clouds and meshes with learning paradigms and applications.
Quick Take
It highlights the impact of dataset design and supervision on advancements in 3D learning, including implicit neural representations and 4D modeling, aiming to unify fragmented perspectives on efficiency and fidelity.
Key Points
- Analyzes structural representations of 3D data: point clouds, meshes, voxels, and 3D Gaussians.
- Examines how dataset design influences 2D-supervised 3D learning and implicit neural representations.
- Clarifies relationships among representations, learning paradigms, and tasks like reconstruction and generation.
- Aims to balance efficiency and fidelity in emerging 3D vision trends.
- Provides a conceptual map for better understanding of 3D vision fragmentation.
Paper Resources
Source Excerpt
From the original publisher, up to about 700 charactersarXiv:2606. 04291v1 Announce Type: new Abstract: 3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map.
We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.