# Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

arXiv: https://arxiv.org/abs/2008.12709 · HTML: https://mlsanity.com/paper/2008.12709/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [HoloDiffusion: Training a 3D Diffusion Model using 2D Images](https://mlsanity.com/paper/2303.16509/) (2023)
- [Virtual Correspondence: Humans as a Cue for Extreme-View Geometry](https://mlsanity.com/paper/2206.08365/) (2022)
- [To The Point: Correspondence-driven monocular 3D category reconstruction](https://mlsanity.com/paper/2106.05662/) (2021)
- [CoCoNets: Continuous Contrastive 3D Scene Representations](https://mlsanity.com/paper/2104.03851/) (2021)
- [StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects](https://mlsanity.com/paper/2105.08016/) (2021)
- [Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields](https://mlsanity.com/paper/2212.02493/) (2022)

## Abstract (arXiv)

We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects. Our method builds in a novel way on concepts from parametric deformation models, non-parametric 3D reconstruction, and canonical embeddings, combining their individual advantages. In particular, it learns to associate each image pixel with a deformation model of the corresponding 3D object point which is canonical, i.e. intrinsic to the identity of the point and shared across objects of the category. The result is a method that, given only sparse 2D supervision at training time, can, at test time, reconstruct the 3D shape and texture of objects from single views, while establishing meaningful dense correspondences between object instances. It also achieves state-of-the-art results in dense 3D reconstruction on public in-the-wild datasets of faces, cars, and birds.