Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields

• URL: http://arxiv.org/abs/2401.16144v1
• Date: Mon, 29 Jan 2024 13:23:34 GMT
• Title: Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields
• Authors: Rongkai Ma, Leo Lebrat, Rodrigo Santa Cruz, Gil Avraham, Yan Zuo, Clinton Fookes, Olivier Salvado
• Abstract summary: Neural radiance fields (NeRFs) have exhibited potential in high-fidelity views of 3D scenes. Standard training paradigm of NeRF presupposes an equal importance for each image in the training set. In this paper, we take a closer look at the implications of the current training paradigm and redesign this for more superior rendering quality.
• Score: 24.99410489251996
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Neural radiance fields (NeRFs) have exhibited potential in synthesizing high-fidelity views of 3D scenes but the standard training paradigm of NeRF presupposes an equal importance for each image in the training set. This assumption poses a significant challenge for rendering specific views presenting intricate geometries, thereby resulting in suboptimal performance. In this paper, we take a closer look at the implications of the current training paradigm and redesign this for more superior rendering quality by NeRFs. Dividing input views into multiple groups based on their visual similarities and training individual models on each of these groups enables each model to specialize on specific regions without sacrificing speed or efficiency. Subsequently, the knowledge of these specialized models is aggregated into a single entity via a teacher-student distillation paradigm, enabling spatial efficiency for online render-ing. Empirically, we evaluate our novel training framework on two publicly available datasets, namely NeRF synthetic and Tanks&Temples. Our evaluation demonstrates that our DaC training pipeline enhances the rendering quality of a state-of-the-art baseline model while exhibiting convergence to a superior minimum.

Related papers

• Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization [30.707317084452594]
  radiance field models are designed to represent 3D content by that training models for each individual scene. This unique characteristic of scene representation and per-scene training distinguishes radiance field models from other neural models. We propose content?aware radiance fields, aligning the model complexity with the scene intricacies through Adversarial Content-Aware Quantization (A-CAQ)
  arXiv  Detail & Related papers  (2024-10-25T11:39:55Z)
• IOVS4NeRF:Incremental Optimal View Selection for Large-Scale NeRFs [3.9248546555042365]
  This paper introduces an innovative incremental optimal view selection framework, IOVS4NeRF, designed to model a 3D scene within a restricted input budget. By selecting views that offer the highest information gain, the quality of novel view synthesis can be enhanced with minimal additional resources.
  arXiv  Detail & Related papers  (2024-07-26T09:11:25Z)
• 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)
• 3D Visibility-aware Generalizable Neural Radiance Fields for Interacting Hands [51.305421495638434]
  Neural radiance fields (NeRFs) are promising 3D representations for scenes, objects, and humans. This paper proposes a generalizable visibility-aware NeRF framework for interacting hands. Experiments on the Interhand2.6M dataset demonstrate that our proposed VA-NeRF outperforms conventional NeRFs significantly.
  arXiv  Detail & Related papers  (2024-01-02T00:42:06Z)
• Self-Evolving Neural Radiance Fields [31.124406548504794]
  We propose a novel framework, dubbed Self-Evolving Neural Radiance Fields (SE-NeRF), that applies a self-training framework to neural radiance field (NeRF) We formulate few-shot NeRF into a teacher-student framework to guide the network to learn a more robust representation of the scene. We show and evaluate that applying our self-training framework to existing models improves the quality of the rendered images and achieves state-of-the-art performance in multiple settings.
  arXiv  Detail & Related papers  (2023-12-02T02:28:07Z)
• Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day [63.96075838322437]
  We propose a framework to learn a single-image novel-view synthesizer. Our framework is able to reduce the total training time from 10 days to less than 1 day.
  arXiv  Detail & Related papers  (2023-10-04T17:57:07Z)
• AutoNeRF: Training Implicit Scene Representations with Autonomous Agents [42.90747351247687]
  Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. We present AutoNeRF, a method to collect data required to train NeRFs using autonomous embodied agents.
  arXiv  Detail & Related papers  (2023-04-21T20:22:17Z)
• Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction [77.69363640021503]
  3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. We present SSDNeRF, a unified approach that employs an expressive diffusion model to learn a generalizable prior of neural radiance fields (NeRF) from multi-view images of diverse objects.
  arXiv  Detail & Related papers  (2023-04-13T17:59:01Z)
• Mask-Based Modeling for Neural Radiance Fields [20.728248301818912]
  In this work, we unveil that 3D implicit representation learning can be significantly improved by mask-based modeling. We propose MRVM-NeRF, which is a self-supervised pretraining target to predict complete scene representations from partially masked features along each ray. With this pretraining target, MRVM-NeRF enables better use of correlations across different points and views as the geometry priors.
  arXiv  Detail & Related papers  (2023-04-11T04:12:31Z)
• 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)
• MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo [52.329580781898116]
  We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images, we propose a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference.
  arXiv  Detail & Related papers  (2021-03-29T13:15:23Z)

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.