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

Hugging Face Daily Papers Papers
3d-vision survey taxonomy point-clouds implicit-neural-representations reconstruction generation

Summary

This paper presents a comprehensive taxonomy of 3D vision research, covering geometric representations, datasets, learning paradigms, and applications in reconstruction, generation, and video modeling.

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.
Original Article
View Cached Full Text

Cached at: 06/08/26, 07:17 PM

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

Source: https://huggingface.co/papers/2606.04291 Published on Jun 2

·

Submitted byhttps://huggingface.co/zli12321

LZXon Jun 8

Authors:

,

,

,

,

,

,

,

,

,

Abstract

3D vision research is organized through a taxonomy connecting geometric representations, datasets, learning frameworks, and applications across reconstruction, generation, and video modeling tasks.

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 connectsgeometric 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, and3D Gaussians--along with their acquisition pipelines. We then examine howdataset design,benchmark construction, andsupervision regimesshape recent advances, spanning2D-supervised 3D learning,implicit neural representations, and4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks inreconstruction,generation, andvideo modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and towardmultimodal geometric grounding.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.04291

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.04291 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.04291 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.04291 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Hugging Face Daily Papers

This paper introduces DataComp-VLM (DCVLM), a comprehensive benchmark for evaluating data curation strategies for vision-language models. The authors find that data mixing, rather than filtering, significantly improves performance, and their resulting DCVLM-Baseline dataset achieves state-of-the-art results on 33 downstream tasks.