SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.09088 · 2020

DeepGMR: Learning Latent Gaussian Mixture Models for Registration

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 3 failures of our instrument; 1 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/2008.09088.json · badge: /api/ran/2008.09088.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
vinits5/learning3d extension (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
gmm_params Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vinits5/learning3d/models/deepgmr.py
code served (permissive licence) · get_code("874b9adae4b49026")
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) and returned tuple. 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

torch.manual_seed(0)

# gamma: B x N x J
# B = batch size = 2
# N = number of points = 4
# J = number of components = 3
gamma = torch.randn(2, 4, 3)
gamma = torch.softmax(gamma, dim=2)  # normalize to valid probabilities

# pts: B x N x 3
# B = batch size = 2
# N = number of points = 4
# 3 = spatial coordinates
pts = torch.randn(2, 4, 3)

ARGS = {
    "gamma": gamma,
    "pts": pts,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
gmm_register Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vinits5/learning3d/models/deepgmr.py
code served (permissive licence) · get_code("04d0d489b8695505")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Based on the function signature and body:
# pi_s: B x J (batch size B, number of components J)
# mu_s: B x J x 3 (source means)
# mu_t: B x J x 3 (target means)
# sigma_t: B x J x 3 x 3 (target covariances)

B = 2  # batch size
J = 4  # number of Gaussian components

# pi_s: B x J - mixture weights (should sum to 1 per batch, but function doesn't enforce)
pi_s = torch.rand(B, J)
pi_s = pi_s / pi_s.sum(dim=1, keepdim=True)  # normalize to sum to 1

# mu_s: B x J x 3 - source means
mu_s = torch.randn(B, J, 3)

# mu_t: B x J x 3 - target means
mu_t = torch.randn(B, J, 3)

# sigma_t: B x J x 3 x 3 - target covariances (must be invertible)
# Create positive definite matrices
sigma_t = torch.randn(B, J, 3, 3)
sigma_t = sigma_t @ sigma_t.transpose(-2, -1)  # make symmetric positive definite
sigma_t = sigma_t + torch.eye(3).unsqueeze(0).unsqueeze(0) * 2  # ensure well-conditioned

ARGS = {
    "pi_s": pi_s,
    "mu_s": mu_s,
    "mu_t": mu_t,
    "sigma_t": sigma_t,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
rmse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vinits5/learning3d/examples/train_deepgmr.py
code served (permissive licence) · get_code("7d9486b5108c6d07")
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) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# pts: shape (batch, num_points, 3) - 3D points
# T: shape (batch, 4, 4) - transformation matrices
# T_gt: shape (batch, 4, 4) - ground truth transformation matrices

batch_size = 2
num_points = 4
point_dim = 3

pts = torch.randn(batch_size, num_points, point_dim)
T = torch.randn(batch_size, 4, 4)
T_gt = torch.randn(batch_size, 4, 4)

ARGS = {
    "pts": pts,
    "T": T,
    "T_gt": T_gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
translation_error Ran
ran, honoured the contract we drafted
vinits5/learning3d/examples/train_deepgmr.py
code served (permissive licence) · get_code("6c0ade63ec175cfb")
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) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function computes the norm of the difference between two tensors along dimension 1
# Both t and t_gt should be 2D tensors where we compute norms across dimension 1
# Using batch size 2 and feature dimension 4

t = torch.randn(2, 4)
t_gt = torch.randn(2, 4)

ARGS = {
    "t": t,
    "t_gt": t_gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
rotation_error Not yet run
unverified (harvested, no recorded run)
vinits5/learning3d/examples/train_deepgmr.py
code served (permissive licence) · get_code("d3a525abb9f51399")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. For the last few decades, existing registration algorithms have struggled in situations with large transformations, noise, and time constraints. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method that explicitly leverages a probabilistic registration paradigm by formulating registration as the minimization of KL-divergence between two probability distributions modeled as mixtures of Gaussians. We design a neural network that extracts pose-invariant correspondences between raw point clouds and Gaussian Mixture Model (GMM) parameters and two differentiable compute blocks that recover the optimal transformation from matched GMM parameters. This construction allows the network learn an SE(3)-invariant feature space, producing a global registration method that is real-time, generalizable, and robust to noise. Across synthetic and real-world data, our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods.

For agents

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

get_harvested_code_for_paper("2008.09088")
get_code_for_paper("2008.09088")
have("2008.09088")

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

curl https://syntology.ai/api/ran/2008.09088.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.09088.svg)](https://syntology.ai/paper/2008.09088)

Connect an agent — have() is free.