Papers › Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields

Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields

5 Dec 2022CVPR 2023 1arXiv:2212.02493archive 2025-07-28

Rohith Agaram, Shaurya Dewan, Rahul Sajnani, Adrien Poulenard, Madhava Krishna, Srinath Sridhar

Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it remains challenging to build neural fields for categories of objects without datasets like ShapeNet that provide "canonicalized" object instances that are consistently aligned for their 3D position and orientation (pose). We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs). CaFi-Net directly learns from continuous and noisy radiance fields using a Siamese network architecture that is designed to extract equivariant field features for category-level canonicalization. During inference, our method takes pre-trained neural radiance fields of novel object instances at arbitrary 3D pose and estimates a canonical field with consistent 3D pose across the entire category. Extensive experiments on a new dataset of 1300 NeRF models across 13 object categories show that our method matches or exceeds the performance of 3D point cloud-based methods.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

brown-ivl/Cafi-Net officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

NeRFObjectSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Siamese Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections