Analysis of Sampling Strategies for Implicit 3D Reconstruction
Not on the map. Why?
Abstract (arXiv)
In the training process of the implicit 3D reconstruction network, the choice of spatial query points' sampling strategy affects the final performance of the model. Different works have differences in the selection of sampling strategies, not only in the spatial distribution of query points but also in the order of magnitude difference in the density of query points. For how to select the sampling strategy of query points, current works are more akin to an enumerating operation to find the optimal solution, which seriously affects work efficiency. In this work, we explored the relationship between sampling strategy and network final performance through classification analysis and experimental comparison from three aspects: the relationship between network type and sampling strategy, the relationship between implicit function and sampling strategy, and the impact of sampling density on model performance. In addition, we also proposed two methods, linear sampling and distance mask, to improve the sampling strategy of query points, making it more general and robust.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 32 references that are in the map. First posted on arXiv 8 Apr 2023.
Builds on
30 of 32 references.
References · 30
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
- 2020Convolutional Occupancy Networkscited by 761
- 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
- 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
- 2020Local Implicit Grid Representations for 3D Scenescited by 373
- 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
18 more
- 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
- 2021Neural RGB-D Surface Reconstructioncited by 313
- 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
- 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
- 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Modelscited by 67
- 2020Curriculum DeepSDFcited by 62
- 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
- 20213D Shape Generation with Grid-based Implicit Functionscited by 48
- 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
- 2020D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Imagescited by 42
- 2018Learning 3D Shape Completion under Weak Supervisioncited by 40
- 2021Deep Implicit Surface Point Prediction Networkscited by 40
- 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
- 2020On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapescited by 29
- 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 29
- 2021AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representationscited by 13
- 2022ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fieldscited by 9
- 2022NeuralMeshing: Differentiable Meshing of Implicit Neural Representationscited by 3
Built on by
Not cited yet.