# Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation

arXiv: https://arxiv.org/abs/2509.20681 · HTML: https://mlsanity.com/paper/2509.20681/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2206.05737/) (2022)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [Learning Models as Functionals of Signed-Distance Fields for Manipulation Planning](https://mlsanity.com/paper/2110.00792/) (2021)
- [SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization](https://mlsanity.com/paper/2407.14257/) (2024)
- [RecGS: Removing Water Caustic with Recurrent Gaussian Splatting](https://mlsanity.com/paper/2407.10318/) (2024)
- [GenS: Generalizable Neural Surface Reconstruction from Multi-View Images](https://mlsanity.com/paper/2406.02495/) (2024)
- [Configuration Space Distance Fields for Manipulation Planning](https://mlsanity.com/paper/2406.01137/) (2024)
- [V-PRISM: Probabilistic Mapping of Unknown Tabletop Scenes](https://mlsanity.com/paper/2403.08106/) (2024)
- [Predicted Composite Signed-Distance Fields for Real-Time Motion Planning in Dynamic Environments](https://mlsanity.com/paper/2008.00969/) (2020)
- [SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting](https://mlsanity.com/paper/2507.15602/) (2025)
- [RAMP: Hierarchical Reactive Motion Planning for Manipulation Tasks Using Implicit Signed Distance Functions](https://mlsanity.com/paper/2305.10534/) (2023)
- [Stochastic Implicit Neural Signed Distance Functions for Safe Motion Planning under Sensing Uncertainty](https://mlsanity.com/paper/2309.16862/) (2023)
- [Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments](https://mlsanity.com/paper/2502.02664/) (2025)
- [From Single Images to Motion Policies via Video-Generation Environment Representations](https://mlsanity.com/paper/2505.19306/) (2025)

## Abstract (arXiv)

Implicit representations have been widely applied in robotics for obstacle avoidance and path planning. In this paper, we explore the problem of constructing an implicit distance representation from a single image. Past methods for implicit surface reconstruction, such as NeuS and its variants generally require a large set of multi-view images as input, and require long training times. In this work, we propose Fast Image-to-Neural Surface (FINS), a lightweight framework that can reconstruct high-fidelity surfaces and SDF fields based on a single or a small set of images. FINS integrates a multi-resolution hash grid encoder with lightweight geometry and color heads, making the training via an approximate second-order optimizer highly efficient and capable of converging within a few seconds. Additionally, we achieve the construction of a neural surface requiring only a single RGB image, by leveraging pre-trained foundation models to estimate the geometry inherent in the image. Our experiments demonstrate that under the same conditions, our method outperforms state-of-the-art baselines in both convergence speed and accuracy on surface reconstruction and SDF field estimation. Moreover, we demonstrate the applicability of FINS for robot surface following tasks and show its scalability to a variety of benchmark datasets. Code is publicly available at https://github.com/waynechu1109/FINS.