# Delta-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer

arXiv: https://arxiv.org/abs/2511.20804 · HTML: https://mlsanity.com/paper/2511.20804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images](https://mlsanity.com/paper/2305.17398/) (2023)
- [Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras](https://mlsanity.com/paper/2203.08896/) (2022)
- [Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry](https://mlsanity.com/paper/2104.09877/) (2021)
- [SparseSat-NeRF: Dense Depth Supervised Neural Radiance Fields for Sparse Satellite Images](https://mlsanity.com/paper/2309.00277/) (2023)
- [IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment](https://mlsanity.com/paper/2312.05748/) (2023)

## Abstract (arXiv)

Neural Radiance Fields (NeRFs) have demonstrated remarkable capabilities in 3D reconstruction and novel view synthesis. However, most existing NeRF frameworks require complete retraining when new views are introduced incrementally, limiting their applicability in domains where data arrives sequentially. This limitation is particularly problematic in satellite-based terrain analysis, where regions are repeatedly observed over time. Incremental refinement of NeRFs remains underexplored, and naive approaches suffer from catastrophic forgetting when past data is unavailable. We propose Delta-NeRF, a unique modular residual framework for incremental NeRF refinement. Delta-NeRF introduces several novel techniques including: (1) a residual controller that injects per-layer corrections into a frozen base NeRF, enabling refinement without access to past data; (2) an uncertainty-aware gating mechanism that prevents overcorrection by adaptively combining base and refined predictions; and (3) a view selection strategy that reduces training data by up to 47% while maintaining performance. Additionally, we employ knowledge distillation to compress the enhanced model into a compact student network (20% of original size). Experiments on satellite imagery demonstrate that Delta-NeRF achieves performance comparable to joint training while reducing training time by 30-42%. Delta-NeRF consistently outperforms existing baselines, achieving an improvement of up to 43.5% in PSNR over naive fine-tuning and surpassing joint training on some metrics.