# DARF: Depth-Aware Generalizable Neural Radiance Field

arXiv: https://arxiv.org/abs/2212.02280 · HTML: https://mlsanity.com/paper/2212.02280/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2022.

## Built on by (most cited first, 7 of 7)

- [SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions](https://mlsanity.com/paper/2309.03955/) (2023)
- [UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving](https://mlsanity.com/paper/2311.16945/) (2023)
- [Frequency-Modulated Point Cloud Rendering with Easy Editing](https://mlsanity.com/paper/2303.07596/) (2023)
- [MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition](https://mlsanity.com/paper/2506.23283/) (2025)
- [CEI-3D: Collaborative Explicit-Implicit 3D Reconstruction for Realistic and Fine-Grained Object Editing](https://mlsanity.com/paper/2603.11810/) (2026)
- [Hybrid bundle-adjusting 3D Gaussians for view consistent rendering with pose optimization](https://mlsanity.com/paper/2410.13280/) (2024)
- [HPR3D: Hierarchical Proxy Representation for High-Fidelity 3D Reconstruction and Controllable Editing](https://mlsanity.com/paper/2507.11971/) (2025)

## Abstract (arXiv)

Neural Radiance Field (NeRF) has revolutionized novel-view rendering tasks and achieved impressive results. However, the inefficient sampling and per-scene optimization hinder its wide applications. Though some generalizable NeRFs have been proposed, the rendering quality is unsatisfactory due to the lack of geometry and scene uniqueness. To address these issues, we propose the Depth-Aware Generalizable Neural Radiance Field (DARF) with a Depth-Aware Dynamic Sampling (DADS) strategy to perform efficient novel view rendering and unsupervised depth estimation on unseen scenes without per-scene optimization. Distinct from most existing generalizable NeRFs, our framework infers the unseen scenes on both pixel level and geometry level with only a few input images. By introducing a pre-trained depth estimation module to derive the depth prior, narrowing down the ray sampling interval to the proximity space of the estimated surface, and sampling in expectation maximum position, we preserve scene characteristics while learning common attributes for novel-view synthesis. Moreover, we introduce a Multi-level Semantic Consistency loss (MSC) to assist with more informative representation learning. Extensive experiments on indoor and outdoor datasets show that compared with state-of-the-art generalizable NeRF methods, DARF reduces samples by 50%, while improving rendering quality and depth estimation. Our code is available on https://github.com/shiyue001/GARF.git.