# Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

arXiv: https://arxiv.org/abs/2404.17528 · HTML: https://mlsanity.com/paper/2404.17528/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 46 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [Is Attention All That NeRF Needs?](https://mlsanity.com/paper/2207.13298/) (2022)
- [Explicit Correspondence Matching for Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2304.12294/) (2023)
- [Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency](https://mlsanity.com/paper/1905.02706/) (2019)

## Built on by (most cited first, 8 of 8)

- [MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2405.12218/) (2024)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo](https://mlsanity.com/paper/2412.19130/) (2024)
- [Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction](https://mlsanity.com/paper/2505.19793/) (2025)
- [Geometric Neural Process Fields](https://mlsanity.com/paper/2502.02338/) (2025)
- [C3-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting](https://mlsanity.com/paper/2508.20754/) (2025)
- [Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction](https://mlsanity.com/paper/2603.18306/) (2026)
- [Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives](https://mlsanity.com/paper/2603.20128/) (2026)

## Abstract (arXiv)

Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing methods show limited generalization ability in challenging conditions due to inaccurate geometry, sub-optimal descriptors, and decoding strategies. We address these issues point by point. First, we find the variance-based cost volume exhibits failure patterns as the features of pixels corresponding to the same point can be inconsistent across different views due to occlusions or reflections. We introduce an Adaptive Cost Aggregation (ACA) approach to amplify the contribution of consistent pixel pairs and suppress inconsistent ones. Unlike previous methods that solely fuse 2D features into descriptors, our approach introduces a Spatial-View Aggregator (SVA) to incorporate 3D context into descriptors through spatial and inter-view interaction. When decoding the descriptors, we observe the two existing decoding strategies excel in different areas, which are complementary. A Consistency-Aware Fusion (CAF) strategy is proposed to leverage the advantages of both. We incorporate the above ACA, SVA, and CAF into a coarse-to-fine framework, termed Geometry-aware Reconstruction and Fusion-refined Rendering (GeFu). GeFu attains state-of-the-art performance across multiple datasets. Code is available at https://github.com/TQTQliu/GeFu .