# Learning Free-Form Deformations for 3D Object Reconstruction

Source: [Learning Free-Form Deformations for 3D Object Reconstruction](<https://www.sota2.com/research/paper/68fa654a1e209131cea094cb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:22:52.893Z

Authors: Dominic Jack, Jhony K. Pontes, Sridha Sridharan, Clinton Fookes, Sareh Shirazi, Frederic Maire, Anders Eriksson

Published: 2018-03-29T05:56:15.000Z

## Abstract

Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly from advances in computer vision by generalizing 2D convolutions to the 3D setting, they also have several considerable drawbacks. The computational complexity of voxel-encodings grows cubically with the resolution thus limiting such representations to low-resolution 3D reconstruction. In an attempt to solve this problem, point cloud representations have been proposed. Although point clouds are more efficient than voxel representations as they only cover surfaces rather than volumes, they do not encode detailed geometric information about relationships between points. In this paper we propose a method to learn free-form deformations (FFD) for the task of 3D reconstruction from a single image. By learning to deform points sampled from a high-quality mesh, our trained model can be used to produce arbitrarily dense point clouds or meshes with fine-grained geometry. We evaluate our proposed framework on both synthetic and real-world data and achieve state-of-the-art results on point-cloud and volumetric metrics. Additionally, we qualitatively demonstrate its applicability to label transferring for 3D semantic segmentation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1803.10932>)

[PDF](<https://arxiv.org/pdf/1803.10932.pdf>)
