A Cookbook of 3D Vision: Data, Learning Paradigms, and Application
Quick Take
This article presents a data-centric taxonomy of 3D vision, linking geometric representations like point clouds and meshes with learning paradigms and applications. 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.
Article Excerpt
From source RSS / original summaryarXiv: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.
Reader Mode unavailable (could not extract clean content).
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 →Optimal Transport Flow Matching by Design
The study presents a novel approach to optimal transport (OT) flow matching, reformulating the problem by treating the prior as a design choice. This method achieves over 2x reduction in trajectory curvature compared to existing methods, improving generation quality in few-step regimes without altering the flow model. The approach integrates seamlessly with latent-space models and classifier-free guidance.