Dynamic NeRF: A Review

TL;DR

Dynamic NeRF extends the original NeRF to dynamic scenes by injecting time or deformation into the scene representation. The review explains the canonical NeRF formulation, where a 5D function $F_\Theta:(x,y,z,\theta,\phi) \rightarrow (r,g,b,\sigma)$ is learned by an MLP and rendered via volume integration, and then surveys three dominant dynamic strategies: time-conditioned encoding, deforming ray bending, and skeleton-driven deformation. It provides a structured taxonomy, year-by-year progress (2021–2023), and a cross-paper comparative analysis highlighting trends, venues, and object categories, with data-rich tables and figures. The analysis points to rapid growth in 2023 toward real-time, scalable, and editable dynamic NeRFs, the emergence of human-centric Dynamic NeRFs, and evolving representations (e.g., hash-based, 4D tensor approaches) that balance rendering speed and quality. Overall, the review frames Dynamic NeRF as pivotal for practical 3D reconstruction and editable scene understanding, guiding future work toward robust, scalable, and interactive dynamic neural rendering.

Abstract

Neural Radiance Field(NeRF) is an novel implicit method to achieve the 3D reconstruction and representation with a high resolution. After the first research of NeRF is proposed, NeRF has gained a robust developing power and is booming in the 3D modeling, representation and reconstruction areas. However the first and most of the followed research projects based on NeRF is static, which are weak in the practical applications. Therefore, more researcher are interested and focused on the study of dynamic NeRF that is more feasible and useful in practical applications or situations. Compared with the static NeRF, implementing the Dynamic NeRF is more difficult and complex. But Dynamic is more potential in the future even is the basic of Editable NeRF. In this review, we made a detailed and abundant statement for the development and important implementation principles of Dynamci NeRF. The analysis of main principle and development of Dynamic NeRF is from 2021 to 2023, including the most of the Dynamic NeRF projects. What is more, with colorful and novel special designed figures and table, We also made a detailed comparison and analysis of different features of various of Dynamic. Besides, we analyzed and discussed the key methods to implement a Dynamic NeRF. The volume of the reference papers is large. The statements and comparisons are multidimensional. With a reading of this review, the whole development history and most of the main design method or principles of Dynamic NeRF can be easy understood and gained.

Figures (8)

• Figure 1: Time Development Chart of Dynamic NeRF.
• Figure 2: Basic Method and Principle of Original NeRF.
• Figure 3: Comparison and Analysis of Dynamic NeRF from 2021 to 2023.
• Figure 4: Design main structure of D-NeRF on each main function of the structure.
• Figure 5: Design and functions of $t$ canonical deformation MLP $\Phi_{t}$ and encoding MLP canonical configuration deformation $\Phi_{x}$.