ResFields: Residual Neural Fields for Spatiotemporal Signals

• URL: http://arxiv.org/abs/2309.03160v5
• Date: Sun, 11 Feb 2024 10:37:03 GMT
• Title: ResFields: Residual Neural Fields for Spatiotemporal Signals
• Authors: Marko Mihajlovic, Sergey Prokudin, Marc Pollefeys, Siyu Tang
• Abstract summary: ResFields is a novel class of networks specifically designed to effectively represent complex temporal signals. We conduct comprehensive analysis of the properties of ResFields and propose a matrix factorization technique to reduce the number of trainable parameters. We demonstrate the practical utility of ResFields by showcasing its effectiveness in capturing dynamic 3D scenes from sparse RGBD cameras.
• Score: 61.44420761752655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or radiance fields (NeRFs), via a single multi-layer perceptron (MLP). However, despite the power and simplicity of representing signals with an MLP, these methods still face challenges when modeling large and complex temporal signals due to the limited capacity of MLPs. In this paper, we propose an effective approach to address this limitation by incorporating temporal residual layers into neural fields, dubbed ResFields. It is a novel class of networks specifically designed to effectively represent complex temporal signals. We conduct a comprehensive analysis of the properties of ResFields and propose a matrix factorization technique to reduce the number of trainable parameters and enhance generalization capabilities. Importantly, our formulation seamlessly integrates with existing MLP-based neural fields and consistently improves results across various challenging tasks: 2D video approximation, dynamic shape modeling via temporal SDFs, and dynamic NeRF reconstruction. Lastly, we demonstrate the practical utility of ResFields by showcasing its effectiveness in capturing dynamic 3D scenes from sparse RGBD cameras of a lightweight capture system.

Related papers

• Magnituder Layers for Implicit Neural Representations in 3D [23.135779936528333]
  We introduce a novel neural network layer called the "magnituder" By integrating magnituders into standard feed-forward layer stacks, we achieve improved inference speed and adaptability. Our approach enables a zero-shot performance boost in trained implicit neural representation models.
  arXiv  Detail & Related papers  (2024-10-13T08:06:41Z)
• Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs [26.901819636977912]
  We propose a method that integrates multi-plane representation with a coordinate-based network known for strong bias toward low-frequency signals. We demonstrate that our proposed method outperforms baseline models for both static and dynamic NeRFs with sparse inputs.
  arXiv  Detail & Related papers  (2024-05-13T15:42:46Z)
• Coordinate-Aware Modulation for Neural Fields [11.844561374381575]
  We propose a novel way for exploiting both synthesiss and grid representations in neural fields. We suggest a Neural Coordinate-Aware Modulation (CAM), which modulates the parameters using scale and shift features extracted from the grid representations.
  arXiv  Detail & Related papers  (2023-11-25T10:42:51Z)
• VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis [51.49008959209671]
  We introduce VoxNeRF, a novel approach that leverages volumetric representations to enhance the quality and efficiency of indoor view synthesis. We employ multi-resolution hash grids to adaptively capture spatial features, effectively managing occlusions and the intricate geometry of indoor scenes. We validate our approach against three public indoor datasets and demonstrate that VoxNeRF outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-09T11:32:49Z)
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision [85.17951804790515]
  EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. Our method achieves state-of-the-art performance in sensor simulation.
  arXiv  Detail & Related papers  (2023-11-03T17:59:55Z)
• Adaptive Multi-NeRF: Exploit Efficient Parallelism in Adaptive Multiple Scale Neural Radiance Field Rendering [3.8200916793910973]
  Recent advances in Neural Radiance Fields (NeRF) have demonstrated significant potential for representing 3D scene appearances as implicit neural networks. However, the lengthy training and rendering process hinders the widespread adoption of this promising technique for real-time rendering applications. We present an effective adaptive multi-NeRF method designed to accelerate the neural rendering process for large scenes.
  arXiv  Detail & Related papers  (2023-10-03T08:34:49Z)
• Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos [69.22032459870242]
  We present a novel technique, Residual Radiance Field or ReRF, as a highly compact neural representation to achieve real-time free-view rendering on long-duration dynamic scenes. We show such a strategy can handle large motions without sacrificing quality. Based on ReRF, we design a special FVV that achieves three orders of magnitudes compression rate and provides a companion ReRF player to support online streaming of long-duration FVVs of dynamic scenes.
  arXiv  Detail & Related papers  (2023-04-10T08:36:00Z)
• Factor Fields: A Unified Framework for Neural Fields and Beyond [50.29013417187368]
  We present Factor Fields, a novel framework for modeling and representing signals. Our framework accommodates several recent signal representations including NeRF, Plenoxels, EG3D, Instant-NGP, and TensoRF. Our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks.
  arXiv  Detail & Related papers  (2023-02-02T17:06:50Z)
• 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)

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.