SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.07643 · ICML · 2021

Unsupervised Learning of Visual 3D Keypoints for Control

Pieter Abbeel, Deepak Pathak, Boyuan Chen

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2106.07643.json · badge: /api/ran/2106.07643.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
buoyancy99/unsup-3d-keypoints marked official in Papers with Code
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
CustomeDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("f2205d997c25f553")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CustomeDecoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 3,
    "out_channels": 16,
    "n_filters": 32,
    "groups": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CustomeDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CustomeDecoder output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
CustomeEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("5546c8972dde0b92")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CustomeEncoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_channels": 3,
    "out_channels": 32,
    "n_filters": 32,
    "groups": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CustomeEncoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CustomeEncoder output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
BaseCNN Not yet run
unverified (harvested, no recorded run)
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("b9c4a101ff5bb3af")
How it ran

no invocation recorded.

KeypointNet3d Not yet run
unverified (harvested, no recorded run)
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("814a68a0d1a4f32a")
How it ran

no invocation recorded.

KeypointNetBase Not yet run
unverified (harvested, no recorded run)
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("0d36d42fc4bc30fb")
How it ran

no invocation recorded.

get_cmap Not yet run
unverified (harvested, no recorded run)
buoyancy99/unsup-3d-keypoints/algorithms/common/models/keypoint_net.py
code served (permissive licence) · get_code("174c85c073dd49b0")
How it ran

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

Learning sensorimotor control policies from highdimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms unstructured representations for robotic control. However, most of these representations, whether structured or unstructured are learned in a 2D space even though the control tasks are usually performed in a 3D environment. In this work, we propose a framework to learn such a 3D geometric structure directly from images in an end-toend unsupervised manner. The input images are embedded into latent 3D keypoints via a differentiable encoder which is trained to optimize both a multi-view consistency loss and downstream task objective. These discovered 3D keypoints tend to meaningfully capture robot joints as well as object movements in a consistent manner across both time and 3D space. The proposed approach outperforms prior state-of-art methods across a variety of reinforcement learning benchmarks. Code and videos at https://buoyancy99.github. io/unsup-3d-keypoints/.

For agents

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

get_harvested_code_for_paper("2106.07643")
get_code_for_paper("2106.07643")
have("2106.07643")

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

curl https://syntology.ai/api/ran/2106.07643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.07643.svg)](https://syntology.ai/paper/2106.07643)

Connect an agent — have() is free.