paper-with-me

Papers

Drantal-NeRF: Diffusion-Based Restoration for Anti-aliasing Neural Radiance Field

2024-07-10 · Ganlin Yang, Kaidong Zhang, Jingjing Fu, Dong Liu

Aliasing artifacts in renderings produced by Neural Radiance Field (NeRF) is a long-standing but complex issue in the field of 3D implicit representation, which arises from a multitude of intricate causes and was mitigated by designing more advanced but complex scene parameterization methods before. In this paper, we present a Diffusion-based restoration method for anti-aliasing Neural Radiance Field (Drantal-NeRF). We consider the anti-aliasing issue from a low-level restoration perspective by viewing aliasing artifacts as a kind of degradation model added to clean ground truths. By leveraging the powerful prior knowledge encapsulated in diffusion model, we could restore the high-realism anti-aliasing renderings conditioned on aliased low-quality counterparts. We further employ a feature-wrapping operation to ensure multi-view restoration consistency and finetune the VAE decoder to better adapt to the scene-specific data distribution. Our proposed method is easy to implement and agnostic to various NeRF backbones. We conduct extensive experiments on challenging large-scale urban scenes as well as unbounded 360-degree scenes and achieve substantial qualitative and quantitative improvements.

📄 PDF Abstract BibTeX arXiv:2407.07461

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderNeRF

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

2021-03-24 · ICCV 2021 10 · Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 외

The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images obser…

NeRF

Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields

2023-04-13 · ICCV 2023 1 · Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 외

Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches la…

NeRFNovel View SynthesisSpeech Enhancement

Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering

2023-04-20 · ICCV 2023 1 · Dongting Hu, Zhenkai Zhang, Tingbo Hou, Tongliang Liu 외

The rendering scheme in neural radiance field (NeRF) is effective in rendering a pixel by casting a ray into the scene. However, NeRF yields blurred rendering results when the training images are captured at non-uniform …

NeRFNeural Rendering

Freq-Mip-AA : Frequency Mip Representation for Anti-Aliasing Neural Radiance Fields

2024-06-19 · Youngin Park, Seungtae Nam, Cheul-hee Hahm, Eunbyung Park

Neural Radiance Fields (NeRF) have shown remarkable success in representing 3D scenes and generating novel views. However, they often struggle with aliasing artifacts, especially when rendering images from different came…

NeRF

Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids

2024-05-03 · Junchen Liu, WenBo Hu, Zhuo Yang, Jianteng Chen 외

Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characteri…

NeRF