InterNeRF: Scaling Radiance Fields via Parameter Interpolation
- URL: http://arxiv.org/abs/2406.11737v1
- Date: Mon, 17 Jun 2024 16:55:22 GMT
- Title: InterNeRF: Scaling Radiance Fields via Parameter Interpolation
- Authors: Clinton Wang, Peter Hedman, Polina Golland, Jonathan T. Barron, Daniel Duckworth,
- Abstract summary: We propose InterNeRF, a novel architecture for rendering a target view using a subset of the model's parameters.
We demonstrate significant improvements in multi-room scenes while remaining competitive on standard benchmarks.
- Score: 36.014610797521605
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Neural Radiance Fields (NeRFs) have unmatched fidelity on large, real-world scenes. A common approach for scaling NeRFs is to partition the scene into regions, each of which is assigned its own parameters. When implemented naively, such an approach is limited by poor test-time scaling and inconsistent appearance and geometry. We instead propose InterNeRF, a novel architecture for rendering a target view using a subset of the model's parameters. Our approach enables out-of-core training and rendering, increasing total model capacity with only a modest increase to training time. We demonstrate significant improvements in multi-room scenes while remaining competitive on standard benchmarks.
Related papers
- Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering [10.340739248752516]
We propose Aerial-NeRF to render complex aerial scenes with high-precision.
Our model allows us to perform rendering over 4 times as fast as compared to multiple competitors.
New state-of-the-art results have been achieved on two public large-scale aerial datasets.
arXiv Detail & Related papers (2024-05-10T02:57:02Z) - Global-guided Focal Neural Radiance Field for Large-scale Scene Rendering [12.272724419136575]
We present a global-guided focal neural radiance field (GF-NeRF) that achieves high-fidelity rendering of large-scale scenes.
Our method achieves high-fidelity, natural rendering results on various types of large-scale datasets.
arXiv Detail & Related papers (2024-03-19T15:45:54Z) - 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) - HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces [71.1071688018433]
Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render.
We propose a method, HybridNeRF, that leverages the strengths of both representations by rendering most objects as surfaces.
We improve error rates by 15-30% while achieving real-time framerates (at least 36 FPS) for virtual-reality resolutions (2Kx2K)
arXiv Detail & Related papers (2023-12-05T22:04:49Z) - 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) - Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer
with Mixture-of-View-Experts [88.23732496104667]
Cross-scene generalizable NeRF models have become a new spotlight of the NeRF field.
We bridge "neuralized" architectures with the powerful Mixture-of-Experts (MoE) idea from large language models.
Our proposed model, dubbed GNT with Mixture-of-View-Experts (GNT-MOVE), has experimentally shown state-of-the-art results when transferring to unseen scenes.
arXiv Detail & Related papers (2023-08-22T21:18:54Z) - Grid-guided Neural Radiance Fields for Large Urban Scenes [146.06368329445857]
Recent approaches propose to geographically divide the scene and adopt multiple sub-NeRFs to model each region individually.
An alternative solution is to use a feature grid representation, which is computationally efficient and can naturally scale to a large scene.
We present a new framework that realizes high-fidelity rendering on large urban scenes while being computationally efficient.
arXiv Detail & Related papers (2023-03-24T13:56:45Z) - Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual
Fly-Throughs [54.41204057689033]
We explore how to leverage neural fields (NeRFs) to build interactive 3D environments from large-scale visual captures spanning buildings or even multiple city blocks collected primarily from drone data.
In contrast to the single object scenes against which NeRFs have been traditionally evaluated, this setting poses multiple challenges.
We introduce a simple clustering algorithm that partitions training images (or rather pixels) into different NeRF submodules that can be trained in parallel.
arXiv Detail & Related papers (2021-12-20T17:40:48Z) - RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from
Sparse Inputs [79.00855490550367]
We show that NeRF can produce photorealistic renderings of unseen viewpoints when many input views are available.
We address this by regularizing the geometry and appearance of patches rendered from unobserved viewpoints.
Our model outperforms not only other methods that optimize over a single scene, but also conditional models that are extensively pre-trained on large multi-view datasets.
arXiv Detail & Related papers (2021-12-01T18:59:46Z) - HyperNeRF: A Higher-Dimensional Representation for Topologically Varying
Neural Radiance Fields [45.8031461350167]
A common approach to reconstruct non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space.
We address this limitation by lifting NeRFs into a higher dimensional space, and by representing the 5D radiance field corresponding to each individual input image as a slice through this "hyper-space"
We show that our method, which we dub HyperNeRF, outperforms existing methods on both tasks by significant margins.
arXiv Detail & Related papers (2021-06-24T17:59:03Z)
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.