SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.12796 · NeurIPS · 2022

Non-rigid Point Cloud Registration with Neural Deformation Pyramid

Tatsuya Harada, Yang Li

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 6 failures of our instrument; 2 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/2205.12796.json · badge: /api/ran/2205.12796.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
rabbityl/deformationpyramid canonical (classifier label)
classifier basis: classifier_2025
8 ran · 2 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("f50ca7901ce9b534")
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, MLP: 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
import torch.nn.functional as F

torch.manual_seed(0)

# MLP takes depth and width as parameters
depth = 3
width = 4

ARGS = {
    "depth": depth,
    "width": width
}
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 MLP — 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 MLP 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
NDPLayer Ran
ran on a synthesized input · constructed an object; no result was computed
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("b68bd4fc5a44240b")
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, NDPLayer: 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 = {
    'depth': 3,
    'width': 8,
    'k0': 16,
    'm': 4,
    'rotation_format': 'euler',
    'nonrigidity_est': False,
    'motion': 'SE3',
}
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 NDPLayer — 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 NDPLayer 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
_6d_to_SO3 Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("d1175da13d6a1a9a")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small 6D tensor batch
# Shape: [n, 6] where n=2 (batch size) and 6 is the feature dimension
d6 = torch.randn(2, 6)

ARGS = {
    "d6": d6
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) 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
_copysign Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("aa6de7dd90a78b97")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create two small tensors with distinct shapes to test the function
a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
euler_to_SO3 Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("062db3614d8c0c6f")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) 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)

# Create euler_angles tensor with shape [n, 3]
# Using batch size 2 and 3 euler angles (one for each axis)
euler_angles = torch.randn(2, 3)

# Define convention as a list of 3 distinct axis letters
convention = ['X', 'Y', 'Z']

ARGS = {
    'euler_angles': euler_angles,
    'convention': convention
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) 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
join Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/eval_nolearned.py
code served (permissive licence) · get_code("9289cc672abff866")
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 str. 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 numpy as np

class MockLoader:
    def construct_sequence(self, node):
        # The function expects construct_sequence to return an iterable
        # that can be converted to strings and joined with '_'
        return [1, 2, 3, 'test']

class MockNode:
    pass

torch.manual_seed(0)

loader = MockLoader()
node = MockNode()

ARGS = {
    'loader': loader,
    'node': node
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
quaternion_to_SO3 Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("eb0b7a2a7db8bc29")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) 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)

# Create a batch of 2 quaternions with 4 components each [n, 4]
# Quaternions should be normalized or at least valid for the conversion
quaternions = torch.tensor([
    [1.0, 0.0, 0.0, 0.0],  # identity quaternion
    [0.7071, 0.7071, 0.0, 0.0]  # 90 degree rotation around x-axis
], dtype=torch.float32)

ARGS = {
    "quaternions": quaternions
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) 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
skew Ran
ran; our contract draft was wrong, not the code
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("d4d790ba508bd738")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) 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 expects w to be a tensor where:
# - It indexes w[..., 0], w[..., 1], w[..., 2], so the last dimension must be at least 3
# - It uses torch.zeros_like(w[..., 0]) which works on any shape
# - The output is reshaped to (-1, 3, 3), so the stacked result should flatten to that
# - The stack operation stacks 9 elements along dim=-1, creating a tensor with last dim of 9
# - Before reshape, shape should be (..., 9), and after reshape it becomes (batch, 3, 3)

# Let's create w with shape (2, 3) - batch size 2, 3 components (for 3D vector)
# This will create intermediate shape (2, 9) which reshapes to (2, 3, 3)
w = torch.randn(2, 3)

ARGS = {
    "w": w
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) 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
Deformation_Pyramid Not yet run
unverified (harvested, no recorded run)
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("722c8e905bfd2321")
How it ran

no invocation recorded.

exp_so3 Not yet run
unverified (harvested, no recorded run)
rabbityl/deformationpyramid/model/nets.py
code served (permissive licence) · get_code("770700ff6e9ac321")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

Non-rigid point cloud registration is a key component in many computer vision and computer graphics applications. The high complexity of the unknown non-rigid motion make this task a challenging problem. In this paper, we break down this problem via hierarchical motion decomposition. Our method called Neural Deformation Pyramid (NDP) represents non-rigid motion using a pyramid architecture. Each pyramid level, denoted by a Multi-Layer Perception (MLP), takes as input a sinusoidally encoded 3D point and outputs its motion increments from the previous level. The sinusoidal function starts with a low input frequency and gradually increases when the pyramid level goes down. This allows a multi-level rigid to nonrigid motion decomposition and also speeds up the solving by 50 times compared to the existing MLP-based approach. Our method achieves advanced partialto-partial non-rigid point cloud registration results on the 4DMatch/4DLoMatch benchmark under both no-learned and supervised settings. Code is available at https://github.com/rabbityl/DeformationPyramid. Non-rigid point cloud registration is a key component in many computer vision and computer graphics applications. The goal of non-rigid registration is to find the transformation that maps one point cloud to another. With the availability of consumer range sensors that can measure time-varying surface points, non-rigid registration has been applied to dynamic shape reconstruction problems such as human performance capture, enabling a wide range of applications in XR and robotics. Non-rigid registration is a challenging problem. First, 3D sensor measurements often contain noise, outliers, and occlusions. Occlusions often lead to disconnection of point cloud geometry. Point clouds may also have very low overlap ratios with each other due to the scene deformation and sensor's viewpoint change. The most challenging thing is, unlike rigid registration that only needs to determine the rotation and translation parameters, non-rigid registration needs to estimate the unknown movement of all points, making this problem especially complex to solve. In this paper, we alleviate this complexity through motion decomposition. We observe that natural non-rigid motion usually forms a hierarchical structure: with higher hierarchies representing the global movements and lower hierarchies representing the local deformation. For instance, a walking person can be roughly approximated by three levels: 1) global location and orientation change, 2) local articulated movements from arms, legs, etc, and 3) fine-grained cloth deformation caused by exterior forces. Each level represents motion at a different scale and they have top-down dependencies. Based on this observation, we propose a hierarchical motion representation called Neural Deformation Pyramid (NDP) for non-rigid registration. NDP has a pyramid architecture. Each pyramid level contains a Multi-Layer Perception (MLP) that takes as input a sinusoidally encoded 3D point and outputs its motion increments from the previous level. We found that the frequency of the sinusoidal function controls MLP's capacity of representing non-rigidity: low frequencies yield smooth signals 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

For agents

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

get_harvested_code_for_paper("2205.12796")
get_code_for_paper("2205.12796")
have("2205.12796")

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

curl https://syntology.ai/api/ran/2205.12796.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.12796.svg)](https://syntology.ai/paper/2205.12796)

Connect an agent — have() is free.