SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

• URL: http://arxiv.org/abs/2409.04482v1
• Date: Fri, 6 Sep 2024 03:36:12 GMT
• Title: SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields
• Authors: Yuze Wang, Junyi Wang, Chen Wang, Wantong Duan, Yongtang Bao, Yue Qi,
• Abstract summary: We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. We propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets.
• Score: 9.606992888590757
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost.

Related papers

• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features [65.8738034806085]
  DistillNeRF is a self-supervised learning framework for understanding 3D environments in autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs.
  arXiv  Detail & Related papers  (2024-06-17T21:15:13Z)
• PC-NeRF: Parent-Child Neural Radiance Fields Using Sparse LiDAR Frames in Autonomous Driving Environments [3.1969023045814753]
  We propose a 3D scene reconstruction and novel view synthesis framework called parent-child neural radiance field (PC-NeRF) PC-NeRF implements hierarchical spatial partitioning and multi-level scene representation, including scene, segment, and point levels. With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes.
  arXiv  Detail & Related papers  (2024-02-14T17:16:39Z)
• ReconFusion: 3D Reconstruction with Diffusion Priors [104.73604630145847]
  We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions.
  arXiv  Detail & Related papers  (2023-12-05T18:59:58Z)
• Learning Neural Duplex Radiance Fields for Real-Time View Synthesis [33.54507228895688]
  We propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations. We demonstrate the effectiveness and superiority of our approach via extensive experiments on a range of standard datasets.
  arXiv  Detail & Related papers  (2023-04-20T17:59:52Z)
• Multi-Plane Neural Radiance Fields for Novel View Synthesis [5.478764356647437]
  Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints. In this work, we examine the performance, generalization, and efficiency of single-view multi-plane neural radiance fields. We propose a new multiplane NeRF architecture that accepts multiple views to improve the synthesis results and expand the viewing range.
  arXiv  Detail & Related papers  (2023-03-03T06:32:55Z)
• AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training [100.33713282611448]
  We conduct the first pilot study on training NeRF with high-resolution data. We propose the corresponding solutions, including marrying the multilayer perceptron with convolutional layers. Our approach is nearly free without introducing obvious training/testing costs.
  arXiv  Detail & Related papers  (2022-11-17T17:22:28Z)
• CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations [77.90883737693325]
  This paper proposes CLONeR, which significantly improves upon NeRF by allowing it to model large outdoor driving scenes observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for rendering in metric space.
  arXiv  Detail & Related papers  (2022-09-02T17:44:50Z)
• NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction [50.54946139497575]
  We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We demonstrate that NeRFusion achieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.
  arXiv  Detail & Related papers  (2022-03-21T18:56:35Z)
• Learning Multi-Object Dynamics with Compositional Neural Radiance Fields [63.424469458529906]
  We present a method to learn compositional predictive models from image observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and graph neural networks. NeRFs have become a popular choice for representing scenes due to their strong 3D prior. For planning, we utilize RRTs in the learned latent space, where we can exploit our model and the implicit object encoder to make sampling the latent space informative and more efficient.
  arXiv  Detail & Related papers  (2022-02-24T01:31:29Z)

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.