arXiv cs.AI· Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang·· 3 天前AI 评分22
前馈 3D 场景建模综述：从问题驱动视角看模型设计
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
AI 导读
一篇 67 页、395 篇参考文献的综述提出以模型设计为中心的前馈 3D 重建分类法，抛开隐式场与显式图元等输出表示差异，将研究方向归纳为特征增强、几何感知、模型效率、增强策略和时序感知模型五个关键问题。该综述还系统梳理了相关基准与数据集，并对前馈 3D 模型的实际应用进行分类讨论，最后指出可扩展性、评测标准和世界建模等开放挑战。
正文 · 原文
Authors:Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang
Abstract:Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity, they are limited by slow per-scene optimization or category-specific training, which hinders their practical deployment and scalability. Hence, generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years. By learning a model that maps images directly to 3D representations in a single forward pass, these methods enable efficient reconstruction and robust cross-scene generalization. Our survey is motivated by a critical observation: despite the diverse geometric output representations, ranging from implicit fields to explicit primitives, existing feed-forward approaches share similar high-level architectural patterns, such as image feature extraction backbones, multi-view information fusion mechanisms, and geometry-aware design principles. Consequently, we abstract away from these representation differences and instead focus on model design, proposing a novel taxonomy centered on model design strategies that are agnostic to the output format. Our proposed taxonomy organizes the research directions into five key problems that drive recent research development: feature enhancement, geometry awareness, model efficiency, augmentation strategies and temporal-aware models. To support this taxonomy with empirical grounding and standardized evaluation, we further comprehensively review related benchmarks and datasets, and extensively discuss and categorize real-world applications based on feed-forward 3D models. Finally, we outline future directions to address open challenges such as scalability, evaluation standards, and world modeling.
| Comments: | 67 pages, 395 references. Project page: this https URL. Code: this https URL. This work has been submitted to Springer for possible publication |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR) |
| Cite as: | arXiv:2604.14025 [cs.CV] |
| (or arXiv:2604.14025v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2604.14025 arXiv-issued DOI via DataCite |
Submission history
From: Weijie Wang [view email]
[v1]
Wed, 15 Apr 2026 16:07:18 UTC (13,178 KB)
[v2]
Sat, 10 Oct 2026 07:01:28 UTC (12,577 KB)
来源：arXiv cs.AI · arxiv.org