NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)
read the original abstract
In March 2020, Neural Radiance Field (NeRF) revolutionized Computer Vision, allowing for implicit, neural network-based scene representation and novel view synthesis. NeRF models have found diverse applications in robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, and more. In August 2023, Gaussian Splatting, a direct competitor to the NeRF-based framework, was proposed, gaining tremendous momentum and overtaking NeRF-based research in terms of interest as the dominant framework for novel view synthesis. We present a comprehensive survey of NeRF papers from the past five years (2020-2025). These include papers from the pre-Gaussian Splatting era, where NeRF dominated the field for novel view synthesis and 3D implicit and hybrid representation neural field learning. We also include works from the post-Gaussian Splatting era where NeRF and implicit/hybrid neural fields found more niche applications. Our survey is organized into architecture and application-based taxonomies in the pre-Gaussian Splatting era, as well as a categorization of active research areas for NeRF, neural field, and implicit/hybrid neural representation methods. We provide an introduction to the theory of NeRF and its training via differentiable volume rendering. We also present a benchmark comparison of the performance and speed of classical NeRF, implicit and hybrid neural representation, and neural field models, and an overview of key datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Motion-Enabled Tomography via Gaussian Mixture Models
A parametric GMM model for motion-enabled tomography that decouples reconstruction into sub-problems and tests on 2D simulations of intersecting trajectories.
-
Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
S2C-3D reconstructs complete high-fidelity 3D scenes from as few as 6-8 images by finetuning a diffusion model on scene data, applying consistency-conditioned sampling, and planning trajectories for full coverage.
-
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
MU-GeNeRF combines source-view and target-view uncertainties via a heteroscedastic loss to enable distractor-aware generalizable NeRF reconstruction that matches scene-specific methods.
-
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.
-
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.
-
3D Reconstruction and Knowledge Distillation to Improve Multi-View Image Models to Explore Spike Volume Estimation in Wheat
Knowledge distillation from a rigid-invariant 3D point cloud network into a regulated multi-view Transformer yields lower-error, faster wheat spike volume estimates from 2D images.
-
Safe Navigation using Neural Radiance Fields via Reachable Sets
Safe robot navigation in obstacle-rich environments is demonstrated in simulation by representing obstacles with NeRFs and enforcing safety via reachable-set constraints inside a linear-matrix-inequality optimal-contr...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.