paper-with-me

홈 › Papers

Learning a Diffusion Prior for NeRFs

2023-04-27 · Guandao Yang, Abhijit Kundu, Leonidas J. Guibas, Jonathan T. Barron, Ben Poole

Neural Radiance Fields (NeRFs) have emerged as a powerful neural 3D representation for objects and scenes derived from 2D data. Generating NeRFs, however, remains difficult in many scenarios. For instance, training a NeRF with only a small number of views as supervision remains challenging since it is an under-constrained problem. In such settings, it calls for some inductive prior to filter out bad local minima. One way to introduce such inductive priors is to learn a generative model for NeRFs modeling a certain class of scenes. In this paper, we propose to use a diffusion model to generate NeRFs encoded on a regularized grid. We show that our model can sample realistic NeRFs, while at the same time allowing conditional generations, given a certain observation as guidance.

📄 PDF Abstract BibTeX arXiv:2304.14473

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

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

3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent Diffusion

2023-03-21 · Yu-Jhe Li, Tao Xu, Ji Hou, Bichen Wu 외

We tackle the task of text-to-3D creation with pre-trained latent-based NeRFs (NeRFs that generate 3D objects given input latent code). Recent works such as DreamFusion and Magic3D have shown great success in generating …

Contrastive LearningNeRFText to 3D

DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models

2023-02-23 · CVPR 2023 1 · Jamie Wynn, Daniyar Turmukhambetov

Under good conditions, Neural Radiance Fields (NeRFs) have shown impressive results on novel view synthesis tasks. NeRFs learn a scene's color and density fields by minimizing the photometric discrepancy between training…

DenoisingNeRFNovel View Synthesis

Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes

2024-01-01 · CVPR 2024 1 · Xiaotian Sun, Qingshan Xu, Xinjie Yang, Yu Zang 외

It is challenging for Neural Radiance Fields (NeRFs) in the few-shot setting to reconstruct high-quality novel views and depth maps in 360^\circ outward-facing indoor scenes. The captured sparse views for these scene…

Depth EstimationDepth PredictionMonocular Depth EstimationNeRF

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs

2023-04-20 · ICCV 2023 1 · Frederik Warburg, Ethan Weber, Matthew Tancik, Aleksander Holynski 외

Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as floaters or flawed geometry when rendered outside the camera trajectory. Existing evaluation protocols often do not capture these effects, si…

NeRFNovel View Synthesis

Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction

2023-04-13 · ICCV 2023 1 · Hansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian 외

3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. Despite numerous task-specific methods, developing a comprehensive model remains challenging. In thi…

3D-Aware Image Synthesis3D Generation3D ReconstructionDecoder+4