# DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction

arXiv: https://arxiv.org/abs/1911.09204 · HTML: https://mlsanity.com/paper/1911.09204/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation](https://mlsanity.com/paper/2206.12055/) (2022)
- [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://mlsanity.com/paper/2206.04942/) (2022)
- [Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach](https://mlsanity.com/paper/2109.14982/) (2021)
- [Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape](https://mlsanity.com/paper/2204.04379/) (2022)
- [NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation](https://mlsanity.com/paper/2405.00340/) (2024)
- [3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models](https://mlsanity.com/paper/2210.04265/) (2022)
- [CD2: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distance](https://mlsanity.com/paper/2206.00447/) (2022)

## Abstract (arXiv)

We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality. The metric compares two 3D shapes by measuring distances between multi-view images differentiably rendered from the shapes. Importantly, the image-space distance is also differentiable and measures visual similarity, rather than pixel-wise distortion. Specifically, the similarity is defined by mean-squared errors over HardNet features computed from probabilistic keypoint maps of the compared images. Our differential visual shape similarity metric can be easily plugged into various 3D reconstruction networks, replacing their distortion-based losses, such as Chamfer or Earth Mover distances, so as to optimize the network weights to produce reconstructions with better structural fidelity and visual quality. We demonstrate this both objectively, using well-known shape metrics for retrieval and classification tasks that are independent from our new metric, and subjectively through a perceptual study.