AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

• URL: http://arxiv.org/abs/2410.01202v1
• Date: Wed, 2 Oct 2024 03:10:38 GMT
• Title: AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction
• Authors: Jingnan Gao, Zhuo Chen, Yichao Yan, Xiaokang Yang,
• Abstract summary: We present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.
• Score: 55.69271635843385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rendering while reconstructing accurate geometry remains an unsolved problem. In this work, we present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Different from previous neural surfaces, our fused-granularity geometry structure balances the overall structures and fine geometric details, producing accurate geometry reconstruction. To disambiguate geometry from reflective appearance, we introduce blended radiance fields to model diffuse and specularity following the anisotropic spherical Gaussian encoding, a physics-based rendering pipeline. With these designs, AniSDF can reconstruct objects with complex structures and produce high-quality renderings. Furthermore, our method is a unified model that does not require complex hyperparameter tuning for specific objects. Extensive experiments demonstrate that our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.

Related papers

• DreamPolish: Domain Score Distillation With Progressive Geometry Generation [66.94803919328815]
  We introduce DreamPolish, a text-to-3D generation model that excels in producing refined geometry and high-quality textures. In the geometry construction phase, our approach leverages multiple neural representations to enhance the stability of the synthesis process. In the texture generation phase, we introduce a novel score distillation objective, namely domain score distillation (DSD), to guide neural representations toward such a domain.
  arXiv  Detail & Related papers  (2024-11-03T15:15:01Z)
• RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
  We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor. Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:54:25Z)
• Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement [78.48648360358193]
  We present a novel framework that generates textured surface meshes from images. Our approach begins by efficiently initializing the geometry and view-dependency appearance with a NeRF. We jointly refine the appearance with geometry and bake it into texture images for real-time rendering.
  arXiv  Detail & Related papers  (2023-03-03T17:14:44Z)
• HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces [6.382138631957651]
  We present High-Resolution NeuS, a novel neural implicit surface reconstruction method. HR-NeuS recovers high-frequency surface geometry while maintaining large-scale reconstruction accuracy. We demonstrate through experiments on DTU and BlendedMVS datasets that our approach produces 3D geometries that are qualitatively more detailed and quantitatively of similar accuracy compared to previous approaches.
  arXiv  Detail & Related papers  (2023-02-14T02:25:16Z)
• NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies [87.06532943371575]
  We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation.
  arXiv  Detail & Related papers  (2022-11-25T15:21:45Z)
• 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)
• Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction [41.43563122590449]
  We propose geometry-consistent neural implicit surfaces learning for multi-view reconstruction. Our proposed method achieves high-quality surface reconstruction in both complex thin structures and large smooth regions.
  arXiv  Detail & Related papers  (2022-05-31T14:52:07Z)
• PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis [52.546998369121354]
  We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images. We propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. We show that the introduction of such geometry-aware features helps to achieve a better disentanglement between appearance and geometry.
  arXiv  Detail & Related papers  (2022-02-10T07:39:47Z)
• Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance [46.488713939892136]
  We introduce a neural network that simultaneously learns the unknown geometry, camera parameters, and a neural architecture that approximates the light reflected from the surface towards the camera. We trained our network on real world 2D images of objects with different material properties, lighting conditions, and noisy camera materials from the DTU MVS dataset.
  arXiv  Detail & Related papers  (2020-03-22T10:20:13Z)

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.