用物理约束提升稀疏视角下的3D重建精度
PhysicsNeRF: Physics-Guided 3D Reconstruction from Sparse Views
- 引入深度排序、视图一致性等四类物理约束
- 仅用8张图就达到21.4 dB平均PSNR
- 适合需要物理一致性的智能体交互与仿真
PhysicsNeRF是一种基于物理约束的稀疏视角3D重建框架，通过深度排序、类似RegNeRF的一致性、稀疏先验和跨视图对齐四类互补约束扩展神经辐射场。标准NeRF在稀疏监督下表现不佳，而PhysicsNeRF采用仅0.67M参数的紧凑结构，在仅8个视角下实现了21.4 dB的平均PSNR，优于已有方法。研究发现存在5.7–6.2 dB的泛化差距，揭示了稀疏视角重建的根本局限。该方法可生成物理一致且可泛化的3D表示，适用于智能体交互与仿真，并阐明了约束式NeRF模型在表达能力与泛化性之间的权衡。
原文摘要 · Abstract (English)
PhysicsNeRF is a physically grounded framework for 3D reconstruction from sparse views, extending Neural Radiance Fields with four complementary constraints: depth ranking, RegNeRF-style consistency, sparsity priors, and cross-view alignment. While standard NeRFs fail under sparse supervision, PhysicsNeRF employs a compact 0.67M-parameter architecture and achieves 21.4 dB average PSNR using only 8 views, outperforming prior methods. A generalization gap of 5.7-6.2 dB is consistently observed and analyzed, revealing fundamental limitations of sparse-view reconstruction. PhysicsNeRF enables physically consistent, generalizable 3D representations for agent interaction and simulation, and clarifies the expressiveness-generalization trade-off in constrained NeRF models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。