# ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects

arXiv: https://arxiv.org/abs/2605.29417 · HTML: https://mlsanity.com/paper/2605.29417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids](https://mlsanity.com/paper/1810.01566/) (2018)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos](https://mlsanity.com/paper/2503.17973/) (2025)
- [EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos](https://mlsanity.com/paper/2307.11307/) (2023)
- [A Survey of Non-Rigid 3D Registration](https://mlsanity.com/paper/2203.07858/) (2022)
- [Dynamic Point Fields](https://mlsanity.com/paper/2304.02626/) (2023)
- [Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulation](https://mlsanity.com/paper/2206.02881/) (2022)
- [VIRDO: Visio-tactile Implicit Representations of Deformable Objects](https://mlsanity.com/paper/2202.00868/) (2022)
- [Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth](https://mlsanity.com/paper/2211.14503/) (2022)
- [GraphDistNet: A Graph-based Collision-distance Estimator for Gradient-based Trajectory Optimization](https://mlsanity.com/paper/2206.01517/) (2022)
- [DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action Discretization](https://mlsanity.com/paper/2409.14719/) (2024)
- [Deformable Surface Reconstruction via Riemannian Metric Preservation](https://mlsanity.com/paper/2212.11596/) (2022)
- [Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations](https://mlsanity.com/paper/2505.00500/) (2025)
- [A Visuo-Tactile Data Collection System with Haptic Feedback for Coarse-to-Fine Imitation Learning](https://mlsanity.com/paper/2605.08757/) (2026)

## Abstract (arXiv)

This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipulation. Recent DO reconstruction approaches often adopt implicit neural representations (INRs) to model continuous surfaces as well as capture structural variability. However, these methods typically rely on object-specific shape priors that improve training stability and limit generalization. To figure it out, we introduce ParCo-SDF, a two-stage partial-to-complete signed distance field (SDF) reconstruction framework consisting of temporal geometry encoding followed by FiLM-conditioned SDF prediction. The temporal encoder captures structural similarity across DO sequence, enabling prior-free stable training. FiLM-based conditioning preserves reconstruction expressivity while reducing network complexity. We evaluate the proposed method against a state-of-the-art DO surface reconstruction baseline on a rubber band manipulation dataset, demonstrating robust and high-fidelity reconstruction under severe occlusions.