A Cookbook of 3D Vision: Data, Learning Paradigms, and Application
For researchers and practitioners in 3D vision, this work offers a unified conceptual map to navigate the fragmented field, clarifying relationships among representations and learning paradigms.
This paper provides a comprehensive taxonomy of 3D vision, connecting geometric representations, datasets, learning frameworks, and applications. It analyzes key representations (point clouds, meshes, voxels, 3D Gaussians) and examines how dataset design and supervision regimes shape recent advances, offering a consolidated view of trends toward balancing efficiency and fidelity.
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.