SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.19296 · NeurIPS · 2024

Neural Isometries: Taming Transformations for Equivariant ML

Vincent Sitzmann, Thomas Mitchel, Michael Taylor

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2405.19296.json · badge: /api/ran/2405.19296.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
vsitzmann/neural-isometries canonical (classifier label)
classifier basis: classifier_2025
1 ran · 5 no recorded run
FunctionStatusWhere it lives
safe_inverse Ran
ran, honoured the contract we drafted
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("d3a473dc77cff902")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

orth_mlp Not yet run
unverified (harvested, no recorded run)
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("dc1f79f8150d1905")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

orth_net Not yet run
unverified (harvested, no recorded run)
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("073b7965f19ea854")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

orth_neuron Not yet run
unverified (harvested, no recorded run)
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("a840083a0a16d094")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

orth_norm Not yet run
unverified (harvested, no recorded run)
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("34751275cf8fb232")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

orth_out Not yet run
unverified (harvested, no recorded run)
vsitzmann/neural-isometries/nn/equiv.py
pointer only (licence: NOASSERTION) · get_code("7912ec7278978b97")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vsitzmann/neural-isometries (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related by isometries whenever their corresponding observations are geometrically related in world space. Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian. This approach forms an effective backbone for self-supervised representation learning, and we demonstrate that a simple off-the-shelf equivariant network operating in the pre-trained latent space can achieve results on par with meticulously-engineered, handcrafted networks designed to handle complex, nonlinear symmetries. Furthermore, isometric maps capture information about the respective transformations in world space, and we show that this allows us to regress camera poses directly from the coefficients of the maps between encodings of adjacent views of a scene.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.19296")
get_code_for_paper("2405.19296")
have("2405.19296")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.19296.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.19296.svg)](https://syntology.ai/paper/2405.19296)

Connect an agent — have() is free.