A Probability-guided Sampler for Neural Implicit Surface Rendering

• URL: http://arxiv.org/abs/2506.08619v1
• Date: Tue, 10 Jun 2025 09:28:16 GMT
• Title: A Probability-guided Sampler for Neural Implicit Surface Rendering
• Authors: Gonçalo Dias Pais, Valter Piedade, Moitreya Chatterjee, Marcus Greiff, Pedro Miraldo,
• Abstract summary: Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of synthesized images and surface reconstruction of 3D scenes/objects.<n>A key characteristic is that none can train the neural network with every possible input data, specifically, every pixel and potential 3D point along projection rays.<n>In this paper, we leverage the implicit surface representation of the foreground scene and model a probability density function in a 3D image projection space to achieve a more targeted sampling of the rays toward regions of interest.
• Score: 12.233362977312947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of synthesized images and surface reconstruction of 3D scenes/objects. In all of these methods, a key characteristic is that none can train the neural network with every possible input data, specifically, every pixel and potential 3D point along the projection rays due to scalability issues. While vanilla NeRFs uniformly sample both the image pixels and 3D points along the projection rays, some variants focus only on guiding the sampling of the 3D points along the projection rays. In this paper, we leverage the implicit surface representation of the foreground scene and model a probability density function in a 3D image projection space to achieve a more targeted sampling of the rays toward regions of interest, resulting in improved rendering. Additionally, a new surface reconstruction loss is proposed for improved performance. This new loss fully explores the proposed 3D image projection space model and incorporates near-to-surface and empty space components. By integrating our novel sampling strategy and novel loss into current state-of-the-art neural implicit surface renderers, we achieve more accurate and detailed 3D reconstructions and improved image rendering, especially for the regions of interest in any given scene.

Related papers

• NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface [0.5772546394254112]
  Reconstructing 3D structures from 2D X-ray images is a valuable technique in medical applications that requires less radiation exposure than computed tomography scans.<n>Recent approaches that use implicit neural representations have enabled the synthesis of novel views from sparse X-ray images.<n>We propose a novel approach for reconstructing 3D scenes using a Neural Attenuation Surface (NeAS) that simultaneously captures the surface geometry and attenuation coefficient fields.
  arXiv  Detail & Related papers  (2025-03-10T16:11:58Z)
• Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generation [6.506009070668646]
  This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud.
  arXiv  Detail & Related papers  (2023-10-06T10:55:34Z)
• NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes [56.31855837632735]
  We propose a compact and flexible architecture that enables easy 3D surface reconstruction from any NeRF-driven approach. Our final 3D mesh is physically accurate and can be rendered in real time on an array of devices.
  arXiv  Detail & Related papers  (2023-03-16T16:06:03Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• Neural Poisson: Indicator Functions for Neural Fields [25.41908065938424]
  Implicit neural field generating signed distance field representations (SDFs) of 3D shapes have shown remarkable progress. We introduce a new paradigm for neural field representations of 3D scenes. We show that our approach demonstrates state-of-the-art reconstruction performance on both synthetic and real scanned 3D scene data.
  arXiv  Detail & Related papers  (2022-11-25T17:28:22Z)
• Recovering Fine Details for Neural Implicit Surface Reconstruction [3.9702081347126943]
  We present D-NeuS, a volume rendering neural implicit surface reconstruction method capable to recover fine geometry details. We impose multi-view feature consistency on the surface points, derived by interpolating SDF zero-crossings from sampled points along rays. Our method reconstructs high-accuracy surfaces with details, and outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-11-21T10:06:09Z)
• Neural 3D Reconstruction in the Wild [86.6264706256377]
  We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections. We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
  arXiv  Detail & Related papers  (2022-05-25T17:59:53Z)
• Enhancement of Novel View Synthesis Using Omnidirectional Image Completion [61.78187618370681]
  We present a method for synthesizing novel views from a single 360-degree RGB-D image based on the neural radiance field (NeRF) Experiments demonstrated that the proposed method can synthesize plausible novel views while preserving the features of the scene for both artificial and real-world data.
  arXiv  Detail & Related papers  (2022-03-18T13:49:25Z)
• Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering [60.02806355570514]
  Inferring representations of 3D scenes from 2D observations is a fundamental problem of computer graphics, computer vision, and artificial intelligence. We propose a novel neural scene representation, Light Field Networks or LFNs, which represent both geometry and appearance of the underlying 3D scene in a 360-degree, four-dimensional light field. Rendering a ray from an LFN requires only a *single* network evaluation, as opposed to hundreds of evaluations per ray for ray-marching or based on volumetrics.
  arXiv  Detail & Related papers  (2021-06-04T17:54:49Z)
• Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
  We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views. Our method is supervised and trained on a public dataset of shapes from common object categories.
  arXiv  Detail & Related papers  (2020-08-18T06:33:40Z)

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.