Neural Density-Distance Fields
- URL: http://arxiv.org/abs/2207.14455v1
- Date: Fri, 29 Jul 2022 03:13:25 GMT
- Title: Neural Density-Distance Fields
- Authors: Itsuki Ueda, Yoshihiro Fukuhara, Hirokatsu Kataoka, Hiroaki Aizawa,
Hidehiko Shishido, Itaru Kitahara
- Abstract summary: This paper proposes Neural Density-Distance Field (NeDDF), a novel 3D representation that reciprocally constrains the distance and density fields.
We extend distance field formulation to shapes with no explicit boundary surface, such as fur or smoke, which enable explicit conversion from distance field to density field.
Experiments show that NeDDF can achieve high localization performance while providing comparable results to NeRF on novel view synthesis.
- Score: 9.742650275132029
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The success of neural fields for 3D vision tasks is now indisputable.
Following this trend, several methods aiming for visual localization (e.g.,
SLAM) have been proposed to estimate distance or density fields using neural
fields. However, it is difficult to achieve high localization performance by
only density fields-based methods such as Neural Radiance Field (NeRF) since
they do not provide density gradient in most empty regions. On the other hand,
distance field-based methods such as Neural Implicit Surface (NeuS) have
limitations in objects' surface shapes. This paper proposes Neural
Density-Distance Field (NeDDF), a novel 3D representation that reciprocally
constrains the distance and density fields. We extend distance field
formulation to shapes with no explicit boundary surface, such as fur or smoke,
which enable explicit conversion from distance field to density field.
Consistent distance and density fields realized by explicit conversion enable
both robustness to initial values and high-quality registration. Furthermore,
the consistency between fields allows fast convergence from sparse point
clouds. Experiments show that NeDDF can achieve high localization performance
while providing comparable results to NeRF on novel view synthesis. The code is
available at https://github.com/ueda0319/neddf.
Related papers
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling [0.20287200280084108]
We learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions.
Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance.
arXiv Detail & Related papers (2024-02-14T00:42:19Z) - Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form
Color Estimation Method [24.44659061093503]
We propose a more adaptive method to reduce the shape-radiance ambiguity.
We first estimate the color field based on the density field and posed images in a closed form.
Experimental results show that our method improves the density field of NeRF both qualitatively and quantitatively.
arXiv Detail & Related papers (2023-12-20T02:50:03Z) - 3D Density-Gradient based Edge Detection on Neural Radiance Fields
(NeRFs) for Geometric Reconstruction [0.0]
We show how to generate geometric 3D reconstructions from Neural Radiance Fields (NeRFs) using density gradients and edge detection filters.
Our approach demonstrates the capability to achieve geometric 3D reconstructions with high geometric accuracy on object surfaces and remarkable object completeness.
arXiv Detail & Related papers (2023-09-26T09:56:27Z) - GridPull: Towards Scalability in Learning Implicit Representations from
3D Point Clouds [60.27217859189727]
We propose GridPull to improve the efficiency of learning implicit representations from large scale point clouds.
Our novelty lies in the fast inference of a discrete distance field defined on grids without using any neural components.
We use uniform grids for a fast grid search to localize sampled queries, and organize surface points in a tree structure to speed up the calculation of distances to the surface.
arXiv Detail & Related papers (2023-08-25T04:52:52Z) - Evaluate Geometry of Radiance Fields with Low-frequency Color Prior [27.741607821885673]
A radiance field is an effective representation of 3D scenes, which has been widely adopted in novel-view synthesis and 3D reconstruction.
It is still an open and challenging problem to evaluate the geometry, i.e., the density field, as the ground-truth is almost impossible to obtain.
We propose a novel metric, named Inverse Mean Residual Color (IMRC), which can evaluate the geometry only with the observation images.
arXiv Detail & Related papers (2023-04-10T02:02:57Z) - Behind the Scenes: Density Fields for Single View Reconstruction [63.40484647325238]
Inferring meaningful geometric scene representation from a single image is a fundamental problem in computer vision.
We propose to predict implicit density fields. A density field maps every location in the frustum of the input image to volumetric density.
We show that our method is able to predict meaningful geometry for regions that are occluded in the input image.
arXiv Detail & Related papers (2023-01-18T17:24:01Z) - Neural Vector Fields for Implicit Surface Representation and Inference [73.25812045209001]
Implicit fields have recently shown increasing success in representing and learning 3D shapes accurately.
We develop a novel and yet a fundamental representation considering unit vectors in 3D space and call it Vector Field (VF)
We show the advantages of VF representation, in learning open, closed, or multi-layered as well as piecewise planar surfaces.
arXiv Detail & Related papers (2022-04-13T17:53:34Z) - ImpDet: Exploring Implicit Fields for 3D Object Detection [74.63774221984725]
We introduce a new perspective that views bounding box regression as an implicit function.
This leads to our proposed framework, termed Implicit Detection or ImpDet.
Our ImpDet assigns specific values to points in different local 3D spaces, thereby high-quality boundaries can be generated.
arXiv Detail & Related papers (2022-03-31T17:52:12Z) - Non-line-of-Sight Imaging via Neural Transient Fields [52.91826472034646]
We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging.
Inspired by the recent Neural Radiance Field (NeRF) approach, we use a multi-layer perceptron (MLP) to represent the neural transient field or NeTF.
We formulate a spherical volume NeTF reconstruction pipeline, applicable to both confocal and non-confocal setups.
arXiv Detail & Related papers (2021-01-02T05:20:54Z) - Neural Unsigned Distance Fields for Implicit Function Learning [53.241423815726925]
We propose Neural Distance Fields (NDF), a neural network based model which predicts the unsigned distance field for arbitrary 3D shapes.
NDF represent surfaces at high resolutions as prior implicit models, but do not require closed surface data.
NDF can be used for multi-target regression (multiple outputs for one input) with techniques that have been exclusively used for rendering in graphics.
arXiv Detail & Related papers (2020-10-26T22:49:45Z)
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.