GD^2-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields

• URL: http://arxiv.org/abs/2401.00616v3
• Date: Fri, 29 Mar 2024 11:27:32 GMT
• Title: GD^2-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields
• Authors: Xiao Pan, Zongxin Yang, Shuai Bai, Yi Yang,
• Abstract summary: We propose a Generative Detail compensation framework via GAN and Diffusion. The framework is both inference-time finetuning-free and with vivid plausible details. Experiments on both the synthetic and real-world datasets show that GD$2$-NeRF noticeably improves the details while without per-scene finetuning.
• Score: 41.63632669921749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we focus on the One-shot Novel View Synthesis (O-NVS) task which targets synthesizing photo-realistic novel views given only one reference image per scene. Previous One-shot Generalizable Neural Radiance Fields (OG-NeRF) methods solve this task in an inference-time finetuning-free manner, yet suffer the blurry issue due to the encoder-only architecture that highly relies on the limited reference image. On the other hand, recent diffusion-based image-to-3d methods show vivid plausible results via distilling pre-trained 2D diffusion models into a 3D representation, yet require tedious per-scene optimization. Targeting these issues, we propose the GD$^2$-NeRF, a Generative Detail compensation framework via GAN and Diffusion that is both inference-time finetuning-free and with vivid plausible details. In detail, following a coarse-to-fine strategy, GD$^2$-NeRF is mainly composed of a One-stage Parallel Pipeline (OPP) and a 3D-consistent Detail Enhancer (Diff3DE). At the coarse stage, OPP first efficiently inserts the GAN model into the existing OG-NeRF pipeline for primarily relieving the blurry issue with in-distribution priors captured from the training dataset, achieving a good balance between sharpness (LPIPS, FID) and fidelity (PSNR, SSIM). Then, at the fine stage, Diff3DE further leverages the pre-trained image diffusion models to complement rich out-distribution details while maintaining decent 3D consistency. Extensive experiments on both the synthetic and real-world datasets show that GD$^2$-NeRF noticeably improves the details while without per-scene finetuning.

Related papers

• DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF [50.458896463542494]
  DiSR-NeRF is a diffusion-guided framework for view-consistent super-resolution (SR) NeRF. We propose Iterative 3D Synchronization (I3DS) to mitigate the inconsistency problem via the inherent multi-view consistency property of NeRF.
  arXiv  Detail & Related papers  (2024-04-01T03:06:23Z)
• Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation [28.079441901818296]
  We propose a text-to-3D method for Neural Radiance Fields (NeRFs) that explicitly enforces fine-grained view consistency. Our method achieves state-of-the-art performance over existing text-to-3D methods.
  arXiv  Detail & Related papers  (2023-12-19T01:09:49Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views [47.215089338101066]
  We present Sparse3D, a novel 3D reconstruction method tailored for sparse view inputs. Our approach distills robust priors from a multiview-consistent diffusion model to refine a neural radiance field. By tapping into 2D priors from powerful image diffusion models, our integrated model consistently delivers high-quality results.
  arXiv  Detail & Related papers  (2023-08-27T11:52:00Z)
• 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)
• NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion [107.67277084886929]
  Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. We propose NerfDiff, which addresses this issue by distilling the knowledge of a 3D-aware conditional diffusion model (CDM) into NeRF through synthesizing and refining a set of virtual views at test time. We further propose a novel NeRF-guided distillation algorithm that simultaneously generates 3D consistent virtual views from the CDM samples, and finetunes the NeRF based on the improved virtual views.
  arXiv  Detail & Related papers  (2023-02-20T17:12:00Z)
• NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors [24.05480789681139]
  We propose NeRDi, a single-view NeRF synthesis framework with general image priors from 2D diffusion models. We leverage off-the-shelf vision-language models and introduce a two-section language guidance as conditioning inputs to the diffusion model. We also demonstrate our generalizability in zero-shot NeRF synthesis for in-the-wild images.
  arXiv  Detail & Related papers  (2022-12-06T19:00:07Z)
• DiffRF: Rendering-Guided 3D Radiance Field Diffusion [18.20324411024166]
  We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. In contrast to 2D-diffusion models, our model learns multi-view consistent priors, enabling free-view synthesis and accurate shape generation.
  arXiv  Detail & Related papers  (2022-12-02T14:37:20Z)
• Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations [111.08941206369508]
  We propose Augmented NeRF (Aug-NeRF), which for the first time brings the power of robust data augmentations into regularizing the NeRF training. Our proposal learns to seamlessly blend worst-case perturbations into three distinct levels of the NeRF pipeline. Aug-NeRF effectively boosts NeRF performance in both novel view synthesis and underlying geometry reconstruction.
  arXiv  Detail & Related papers  (2022-07-04T02:27:07Z)

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.