A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

A new arXiv paper presents a data-centric taxonomy of 3D vision, connecting geometric representations, datasets, learning frameworks, and applications into a single conceptual map. The work analyzes principal 3D data structures—point clouds, meshes, voxels, and 3D Gaussians—alongside acquisition pipelines and examines how dataset design and supervision regimes drive advances in 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. The taxonomy aims to clarify relationships among representations and learning paradigms to help unify a fragmented field and guide emerging trends toward balancing efficiency, fidelity, and multimodal geometric grounding.

arXiv: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. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.