neural radiance fields
A technology that represents 3D scenes using neural networks to predict light radiance from various viewpoints, enabling photorealistic 3D rendering and novel view synthesis.
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
- Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty
- Can NeRFs "See" without Cameras?
- Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting
- Flux4D: Flow-based Unsupervised 4D Reconstruction
- Generalizable Hand-Object Modeling from Monocular RGB Images via 3D Gaussians
- KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing
- NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
- NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods
- OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
- Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior
- Spatially-aware Weights Tokenization for NeRF-Language Models
- Spike4DGS: Towards High-Speed Dynamic Scene Rendering with 4D Gaussian Splatting via a Spike Camera Array