Related papers: ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering

ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering

URL: http://arxiv.org/abs/2403.10906v2
Date: Mon, 07 Apr 2025 05:27:55 GMT
Title: ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering
Authors: Seunghyeon Seo, Yeonjin Chang, Jayeon Yoo, Seungwoo Lee, Hojun Lee, Nojun Kwak,
Abstract summary: We propose ARC-NeRF, an effective regularization-based approach with a novel Area Ray Casting strategy.<n>Our ARC-NeRF outperforms its baseline and achieves competitive results on multiple benchmarks with sharply rendered fine details.
Score: 24.521777082791473
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Recent advancements in the Neural Radiance Field (NeRF) have enhanced its capabilities for novel view synthesis, yet its reliance on dense multi-view training images poses a practical challenge, often leading to artifacts and a lack of fine object details. Addressing this, we propose ARC-NeRF, an effective regularization-based approach with a novel Area Ray Casting strategy. While the previous ray augmentation methods are limited to covering only a single unseen view per extra ray, our proposed Area Ray covers a broader range of unseen views with just a single ray and enables an adaptive high-frequency regularization based on target pixel photo-consistency. Moreover, we propose luminance consistency regularization, which enhances the consistency of relative luminance between the original and Area Ray, leading to more accurate object textures. The relative luminance, as a free lunch extra data easily derived from RGB images, can be effectively utilized in few-shot scenarios where available training data is limited. Our ARC-NeRF outperforms its baseline and achieves competitive results on multiple benchmarks with sharply rendered fine details.

Related papers

DivCon-NeRF: Generating Augmented Rays with Diversity and Consistency for Few-shot View Synthesis [24.645337338400335]
We propose DivCon-NeRF, which significantly enhances both diversity and consistency. By introducing inner-sphere augmentation, DivCon-NeRF randomizes angles and distances for diverse viewpoints. Our method significantly reduces floaters and visual distortions, achieving state-of-the-art performance on the Blender, LLFF, and DTU datasets.
arXiv Detail & Related papers (2025-03-17T08:59:34Z)
NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections [57.63028964831785]
Recent works have improved NeRF's ability to render detailed specular appearance of distant environment illumination, but are unable to synthesize consistent reflections of closer content. We address these issues with an approach based on ray tracing. Instead of querying an expensive neural network for the outgoing view-dependent radiance at points along each camera ray, our model casts rays from these points and traces them through the NeRF representation to render feature vectors.
arXiv Detail & Related papers (2024-05-23T17:59:57Z)
Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images [82.1477261107279]
We propose the irradiance fields from sparse LDR panoramic images to increase the observation counts for faithful geometry recovery. Experiments demonstrate that the irradiance fields outperform state-of-the-art methods on both geometry recovery and HDR reconstruction.
arXiv Detail & Related papers (2023-12-26T08:10:22Z)
Efficient Ray Sampling for Radiance Fields Reconstruction [4.004168836949491]
ray sampling strategy profoundly impacts network convergence. We propose a novel ray sampling approach for neural radiance fields. Our method significantly outperforms state-of-the-art techniques on public benchmark datasets.
arXiv Detail & Related papers (2023-08-29T18:11:32Z)
FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis [30.25904672829623]
We propose FlipNeRF, a novel regularization method for few-shot novel view synthesis by utilizing our proposed flipped reflection rays. FlipNeRF is able to estimate more reliable outputs with reducing floating artifacts effectively across the different scene structures.
arXiv Detail & Related papers (2023-06-30T15:11:00Z)
Spatiotemporally Consistent HDR Indoor Lighting Estimation [66.26786775252592]
We propose a physically-motivated deep learning framework to solve the indoor lighting estimation problem. Given a single LDR image with a depth map, our method predicts spatially consistent lighting at any given image position. Our framework achieves photorealistic lighting prediction with higher quality compared to state-of-the-art single-image or video-based methods.
arXiv Detail & Related papers (2023-05-07T20:36:29Z)
TensoIR: Tensorial Inverse Rendering [51.57268311847087]
TensoIR is a novel inverse rendering approach based on tensor factorization and neural fields. TensoRF is a state-of-the-art approach for radiance field modeling.
arXiv Detail & Related papers (2023-04-24T21:39:13Z)
Re-ReND: Real-time Rendering of NeRFs across Devices [56.081995086924216]
Re-ReND is designed to achieve real-time performance by converting the NeRF into a representation that can be efficiently processed by standard graphics pipelines. We find that Re-ReND can achieve over a 2.6-fold increase in rendering speed versus the state-of-the-art without perceptible losses in quality.
arXiv Detail & Related papers (2023-03-15T15:59:41Z)
GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency [31.22435282922934]
We present a novel framework to regularize Neural Radiance Field (NeRF) in a few-shot setting with a geometry-aware consistency regularization. We show that our model achieves competitive results compared to state-of-the-art few-shot NeRF models.
arXiv Detail & Related papers (2023-01-26T05:14:12Z)
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)
Learning Neural Light Fields with Ray-Space Embedding Networks [51.88457861982689]
We propose a novel neural light field representation that is compact and directly predicts integrated radiance along rays. Our method achieves state-of-the-art quality on dense forward-facing datasets such as the Stanford Light Field dataset.
arXiv Detail & Related papers (2021-12-02T18:59:51Z)
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer [78.91753256634453]
We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiables. In this work, we propose DIBR++, a hybrid differentiable which supports these effects by combining specularization and ray-tracing. Compared to more advanced physics-based differentiables, DIBR++ is highly performant due to its compact and expressive model.
arXiv Detail & Related papers (2021-10-30T01:59:39Z)
Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing [49.759478460828504]
Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, lighting and reflectance. ray tracing was introduced for monocular face reconstruction within a classic optimization-based framework. We propose a new method that greatly improves reconstruction quality and robustness in general scenes.
arXiv Detail & Related papers (2021-03-29T08:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.