Re-Nerfing: Improving Novel Views Synthesis through Novel Views Synthesis

• URL: http://arxiv.org/abs/2312.02255v2
• Date: Wed, 17 Apr 2024 17:44:44 GMT
• Title: Re-Nerfing: Improving Novel Views Synthesis through Novel Views Synthesis
• Authors: Felix Tristram, Stefano Gasperini, Nassir Navab, Federico Tombari,
• Abstract summary: Re-Nerfing is a simple and general multi-stage data augmentation approach. We train a NeRF with the available views, then use the optimized NeRF to synthesize pseudo-views around the original ones. We also train a second NeRF with both the original images and the pseudo views masking out uncertain regions.
• Score: 80.3686833921072
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage data augmentation approach that leverages NeRF's own view synthesis ability to address these limitations. With Re-Nerfing, we enhance the geometric consistency of novel views as follows: First, we train a NeRF with the available views. Then, we use the optimized NeRF to synthesize pseudo-views around the original ones with a view selection strategy to improve coverage and preserve view quality. Finally, we train a second NeRF with both the original images and the pseudo views masking out uncertain regions. Extensive experiments applying Re-Nerfing on various pipelines on the mip-NeRF 360 dataset, including Gaussian Splatting, provide valuable insights into the improvements achievable without external data or supervision, on denser and sparser input scenarios. Project page: https://renerfing.github.io

Related papers

• NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning [63.39461847093663]
  We propose NeRF-VPT, an innovative method for novel view synthesis to address these challenges. Our proposed NeRF-VPT employs a cascading view prompt tuning paradigm, wherein RGB information gained from preceding rendering outcomes serves as instructive visual prompts for subsequent rendering stages. NeRF-VPT only requires sampling RGB data from previous stage renderings as priors at each training stage, without relying on extra guidance or complex techniques.
  arXiv  Detail & Related papers  (2024-03-02T22:08:10Z)
• PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields [54.8553158441296]
  We propose a novel visual localization framework, ie, PNeRFLoc, based on a unified point-based representation. On the one hand, PNeRFLoc supports the initial pose estimation by matching 2D and 3D feature points. On the other hand, it also enables pose refinement with novel view synthesis using rendering-based optimization.
  arXiv  Detail & Related papers  (2023-12-17T08:30:00Z)
• NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds [60.1382112938132]
  We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room. NeRF achieves impressive performance in rendering images for novel views similar to the input views while suffering for novel views that are significantly different from the training views.
  arXiv  Detail & Related papers  (2023-04-13T06:40:08Z)
• Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis [12.3338393483795]
  We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-04-11T13:37:17Z)
• ActiveNeRF: Learning where to See with Uncertainty Estimation [36.209200774203005]
  Recently, Neural Radiance Fields (NeRF) has shown promising performances on reconstructing 3D scenes and synthesizing novel views from a sparse set of 2D images. We present a novel learning framework, ActiveNeRF, aiming to model a 3D scene with a constrained input budget.
  arXiv  Detail & Related papers  (2022-09-18T12:09:15Z)
• Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis [35.035125537722514]
  We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. We first train CG-NeRF on multiple 3D scenes of the DTU dataset. We show that CG-NeRF outperforms state-of-the-art generalizable neural rendering methods on various synthetic and real datasets.
  arXiv  Detail & Related papers  (2022-08-09T12:23:48Z)
• View Synthesis with Sculpted Neural Points [64.40344086212279]
  Implicit neural representations have achieved impressive visual quality but have drawbacks in computational efficiency. We propose a new approach that performs view synthesis using point clouds. It is the first point-based method to achieve better visual quality than NeRF while being more than 100x faster in rendering speed.
  arXiv  Detail & Related papers  (2022-05-12T03:54:35Z)
• InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering [55.70938412352287]
  We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints. We achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.
  arXiv  Detail & Related papers  (2021-12-31T11:56:01Z)

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.