# 3D Shape Completion with Test-Time Training

arXiv: https://arxiv.org/abs/2410.18668 · HTML: https://mlsanity.com/paper/2410.18668/

## 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 24 Oct 2024.

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

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D](https://mlsanity.com/paper/2311.16918/) (2023)
- [HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion](https://mlsanity.com/paper/2303.17015/) (2023)
- [A Level Set Theory for Neural Implicit Evolution under Explicit Flows](https://mlsanity.com/paper/2204.07159/) (2022)
- [Breaking Bad: A Dataset for Geometric Fracture and Reassembly](https://mlsanity.com/paper/2210.11463/) (2022)
- [Sketch3T: Test-Time Training for Zero-Shot SBIR](https://mlsanity.com/paper/2203.14691/) (2022)
- [SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator](https://mlsanity.com/paper/2307.08492/) (2023)
- [Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling](https://mlsanity.com/paper/2007.10294/) (2020)
- [Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts](https://mlsanity.com/paper/2303.14152/) (2023)
- [Topology-Aware Latent Diffusion for 3D Shape Generation](https://mlsanity.com/paper/2401.17603/) (2024)
- [NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation](https://mlsanity.com/paper/2403.18241/) (2024)
- [SC-Diff: 3D Shape Completion with Latent Diffusion Models](https://mlsanity.com/paper/2403.12470/) (2024)
- [Representing Shape Collections with Alignment-Aware Linear Models](https://mlsanity.com/paper/2109.01605/) (2021)
- [PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation](https://mlsanity.com/paper/2207.11790/) (2022)
- [DeepMend: Learning Occupancy Functions to Represent Shape for Repair](https://mlsanity.com/paper/2210.05728/) (2022)

## Abstract (arXiv)

This work addresses the problem of textitshape completion, i.e., the task of restoring incomplete shapes by predicting their missing parts. While previous works have often predicted the fractured and restored shape in one step, we approach the task by separately predicting the fractured and newly restored parts, but ensuring these predictions are interconnected. We use a decoder network motivated by related work on the prediction of signed distance functions (DeepSDF). In particular, our representation allows us to consider test-time-training, i.e., finetuning network parameters to match the given incomplete shape more accurately during inference. While previous works often have difficulties with artifacts around the fracture boundary, we demonstrate that our overfitting to the fractured parts leads to significant improvements in the restoration of eight different shape categories of the ShapeNet data set in terms of their chamfer distances.