$Δ$-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer

• URL: http://arxiv.org/abs/2511.20804v1
• Date: Tue, 25 Nov 2025 19:46:15 GMT
• Title: $Δ$-NeRF: Incremental Refinement of Neural Radiance Fields through Residual Control and Knowledge Transfer
• Authors: Kriti Ghosh, Devjyoti Chakraborty, Lakshmish Ramaswamy, Suchendra M. Bhandarkar, In Kee Kim, Nancy O'Hare, Deepak Mishra,
• Abstract summary: $$-NeRF is a unique modular residual framework for incremental NeRF refinement.<n>Experiments on satellite imagery demonstrate that $$-NeRF achieves performance comparable to joint training.
• Score: 7.885378415708355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $Δ$-NeRF, a unique modular residual framework for incremental NeRF refinement. $Δ$-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 $Δ$-NeRF achieves performance comparable to joint training while reducing training time by 30-42\%. $Δ$-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.

Related papers

• DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform [3.44306950522716]
  We present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding.<n>It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views.<n>Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.
  arXiv  Detail & Related papers  (2025-01-22T04:53:12Z)
• Few-shot NeRF by Adaptive Rendering Loss Regularization [78.50710219013301]
  Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF) Recent works demonstrate that the frequency regularization of Positional rendering can achieve promising results for few-shot NeRF. We propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF.
  arXiv  Detail & Related papers  (2024-10-23T13:05:26Z)
• FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors [6.729663383705042]
  We introduce FrugalNeRF, a novel few-shot NeRF framework that leverages weight-sharing voxels across multiple scales to efficiently represent scene details.<n>Our key contribution is a cross-scale geometric adaptation scheme that selects pseudo ground truth depth based on reprojection errors across scales.<n>Experiments on LLFF, DTU, and RealEstate-10K show that FrugalNeRF outperforms other few-shot NeRF methods while significantly reducing training time.
  arXiv  Detail & Related papers  (2024-10-21T17:59:53Z)
• Spatial Annealing for Efficient Few-shot Neural Rendering [73.49548565633123]
  We introduce an accurate and efficient few-shot neural rendering method named textbfSpatial textbfAnnealing regularized textbfNeRF (textbfSANeRF)<n>By adding merely one line of code, SANeRF delivers superior rendering quality and much faster reconstruction speed compared to current few-shot neural rendering methods.
  arXiv  Detail & Related papers  (2024-06-12T02:48:52Z)
• SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance [136.15885067858298]
  This study presents a novel feature-matching-based sparse geometry regularization module, enhanced by a spatially consistent geometry filtering mechanism and a frequency-guided geometric regularization strategy.<n>Our experiments demonstrate that SGCNeRF achieves superior geometry-consistent outcomes and also surpasses FreeNeRF, with improvements of 0.7 dB in PSNR on LLFF and DTU.
  arXiv  Detail & Related papers  (2024-04-01T08:37:57Z)
• ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field [52.09661042881063]
  We propose an approach that models the bfprovenance for each point -- i.e., the locations where it is likely visible -- of NeRFs as a text field. We show that modeling per-point provenance during the NeRF optimization enriches the model with information on leading to improvements in novel view synthesis and uncertainty estimation.
  arXiv  Detail & Related papers  (2024-01-16T06:19:18Z)
• Clean-NeRF: Reformulating NeRF to account for View-Dependent Observations [67.54358911994967]
  This paper proposes Clean-NeRF for accurate 3D reconstruction and novel view rendering in complex scenes. Clean-NeRF can be implemented as a plug-in that can immediately benefit existing NeRF-based methods without additional input.
  arXiv  Detail & Related papers  (2023-03-26T12:24:31Z)
• FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization [32.1581416980828]
  We present Frequency regularized NeRF (FreeNeRF), a surprisingly simple baseline that outperforms previous methods. We analyze the key challenges in few-shot neural rendering and find that frequency plays an important role in NeRF's training.
  arXiv  Detail & Related papers  (2023-03-13T18:59:03Z)
• Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations [111.08941206369508]
  We propose Augmented NeRF (Aug-NeRF), which for the first time brings the power of robust data augmentations into regularizing the NeRF training. Our proposal learns to seamlessly blend worst-case perturbations into three distinct levels of the NeRF pipeline. Aug-NeRF effectively boosts NeRF performance in both novel view synthesis and underlying geometry reconstruction.
  arXiv  Detail & Related papers  (2022-07-04T02:27:07Z)
• UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields [16.826691448973367]
  Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction. However, the increased resolution and model-free nature of such neural fields come at the cost of high training times and excessive memory requirements. We propose a method to exploit the redundancy of NeRF's sample-based computations by partially sharing evaluations across neighboring sample points.
  arXiv  Detail & Related papers  (2022-06-23T19:57:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.