SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.09552 · NeurIPS · 2022

Cross-modal Learning for Image-Guided Point Cloud Shape Completion

Emanuele Aiello, Diego Valsesia, Enrico Magli

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2209.09552.json · badge: /api/ran/2209.09552.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
diegovalsesia/XMFnet canonical (classifier label)
classifier basis not recorded on the link
9 ran · 2 no recorded run
FunctionStatusWhere it lives
batched_index_select Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
diegovalsesia/XMFnet/encoder_dgcnn/dgcnn.py
code served (permissive licence) · get_code("885f06f1d53ff73e")
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, 2, 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 small input tensor with batch size 2
# Using shape (2, 4, 3) - batch=2, dim 1 has size 4, dim 2 has size 3
x = torch.randn(2, 4, 3)

# Create index tensor for selecting along dim=1
# Shape should be (2, 2) to select 2 indices per batch element
index = torch.tensor([[0, 2], [1, 3]], dtype=torch.long)

# dim parameter specifies which dimension to gather along
dim = 1

ARGS = {
    "x": x,
    "dim": dim,
    "index": index,
}
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, 2, 3) — shape (2, 2, 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
collate_fn Ran
ran; our contract draft was wrong, not the code
diegovalsesia/XMFnet/dataloader.py
pointer only (licence: MIT); the stored copy get_code serves, from ciodar/universalattribution, is pointer only (licence: NONE) · get_code("12c09a1a10ca585d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ciodar/universalattribution, and GitHub detected no licence in that repository when it was checked. 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.

convert_binary Ran
ran on a synthesized input
diegovalsesia/XMFnet/weakly_supervised/dataloader_final.py
code served (permissive licence) · get_code("05e58e3b97e78d7d")
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 ndarray, ndim 2, dtype family int, shape (3, 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 numpy as np

# Create a small image matrix for testing
# Using a 4x3 matrix with values between 0 and 255
image_matrix = np.array([
    [50, 100, 150, 200],
    [75, 125, 175, 225],
    [25, 200, 100, 50]
], dtype=np.uint8)

# Define threshold value
thresh_val = 150

ARGS = {
    "image_matrix": image_matrix,
    "thresh_val": thresh_val
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (3, 4) — shape (3, 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
get_graph_feature Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
diegovalsesia/XMFnet/encoder_dgcnn/dgcnn.py
code served (permissive licence) · get_code("9a8756778dd8234a")
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 4, dtype family float; no output shape is stated. 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 and ndim 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)

# Construct a small tensor for x
# Shape: (batch_size, num_dims, num_points)
# batch_size=2, num_dims=4, num_points=3
x = torch.randn(2, 4, 3)

# k parameter for knn
k = 2

# idx parameter (optional, can be None to let function compute it)
idx = None

ARGS = {
    "x": x,
    "k": k,
    "idx": idx
}
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 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
diegovalsesia/XMFnet/decoder/dec_net.py
code served (permissive licence) · get_code("c779aa8bd2f53710")
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 int, shape (2, 3, 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
import torch.nn as nn

torch.manual_seed(0)

# The function knn expects:
# - x: a tensor that will be transposed (2, 1) and have operations like sum, matmul
# - k: an integer for topk selection

# Looking at the function body:
# - x.transpose(2, 1) suggests x has 3 dimensions
# - torch.sum(x ** 2, dim=1, keepdim=True) operates on dim 1
# - The result is used with topk(k=k, dim=-1)
# This suggests x should be shape (batch, num_points, features)

# Create a small tensor: batch_size=2, num_points=4, features=3
x = torch.randn(2, 4, 3)

# k should be less than the number of points
k = 2

ARGS = {
    "x": x,
    "k": k,
}
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 int, shape (2, 3, 2) — shape (2, 3, 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
knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
diegovalsesia/XMFnet/encoder_dgcnn/dgcnn.py
code served (permissive licence) · get_code("cdd0141594039dcb")
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 int, shape (2, 3, 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)

# x is used with:
# - transpose(2, 1): expects 3D tensor
# - matmul with transposed version: matrix multiplication
# - sum(x ** 2, dim=1, keepdim=True): sum over dimension 1
# - topk(k=k, dim=-1): get top k indices along last dimension
# 
# Shape should be (batch, features, num_points) based on the transpose operations
# Let's use batch=2, features=4, num_points=3

x = torch.randn(2, 4, 3)

# k is the number of nearest neighbors to find
# Should be less than num_points (3), so k=2
k = 2

ARGS = {
    "x": x,
    "k": k,
}
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 int, shape (2, 3, 2) — shape (2, 3, 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
rgb2gray_np Ran
ran on a synthesized input
diegovalsesia/XMFnet/weakly_supervised/dataloader_final.py
code served (permissive licence) · get_code("1c1f2166c12f3356")
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 ndarray, 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 numpy as np

# Create a small RGB image array
# Shape: (height, width, channels) where channels includes RGB + potentially alpha
# Using shape (2, 4, 3) to have distinct dimensions: 2 height, 4 width, 3 RGB channels
rgb_image = np.random.rand(2, 4, 3).astype(np.float32)

ARGS = {
    "rgb": rgb_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, 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
rotation_y Ran
ran on a synthesized input
diegovalsesia/XMFnet/dataloader.py
code served (permissive licence) · get_code("e8229d354e97eb2d")
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 ndarray, ndim 2, dtype family float, shape (2, 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 numpy as np

# rotation_y takes two parameters: pts (array of points) and theta (rotation angle)
# The function applies a rotation matrix multiplication: pts @ rotation_matrix.T
# pts should be a 2D array where each row is a 3D point

# Create sample points - using shape (2, 3) for 2 points in 3D space
pts = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=np.float32)

# Create a rotation angle in radians
theta = np.pi / 4  # 45 degrees

ARGS = {
    'pts': pts,
    'theta': theta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
rotation_z Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
diegovalsesia/XMFnet/dataloader.py
code served (permissive licence) · get_code("33077f0f439ded5c")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np

# pts: 3D points array that will be rotated
# The function does: pts @ rotation_matrix.T
# So pts should be a 2D array of shape (N, 3) where N is number of points
pts = np.array([
    [1.0, 0.0, 0.0],
    [0.0, 1.0, 0.0],
    [1.0, 1.0, 1.0],
    [2.0, 3.0, 4.0]
])

# theta: rotation angle in radians
theta = np.pi / 4  # 45 degrees

ARGS = {
    "pts": pts,
    "theta": theta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
batched_index_select Not yet run
unverified (harvested, no recorded run)
diegovalsesia/XMFnet/decoder/dec_net.py
code served (permissive licence) · get_code("74dec069a2ce1eb3")
How it ran

no invocation recorded.

get_graph_feature Not yet run
unverified (harvested, no recorded run)
diegovalsesia/XMFnet/decoder/dec_net.py
code served (permissive licence) · get_code("4afc8385ea7e18d6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 6 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
knn 52 other papers
22 dated earlier, 1 the same month, 29 later · 12 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
2005.06734 (2020-05)
Dense-Resolution Network for Point Cloud Classification and Segmentation
and 49 more not named here
collate_fn 15 other papers
1 dated earlier, 14 later
2003.04618 (2020-03)
Convolutional Occupancy Networks
2301.13823 (2023-01)
Grounding Language Models to Images for Multimodal Inputs and Outputs
2310.05473 (2023-10)
Sentence-level Prompts Benefit Composed Image Retrieval
and 12 more not named here
get_graph_feature 13 other papers
5 dated earlier, 8 later · 2 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
2109.00179 (2021-09)
Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
2111.04426 (2021-11)
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
and 10 more not named here
batched_index_select 1 other paper
1 later
2407.02887 (2024-07)
Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
rotation_y 1 other paper
1 later
ijcai2025_0108 (2025 (year only))
Multi-Modal Point Cloud Completion with Interleaved Attention Enhanced Transformer
rotation_z 1 other paper
1 later
ijcai2025_0108 (2025 (year only))
Multi-Modal Point Cloud Completion with Interleaved Attention Enhanced Transformer

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 2026-11-21.

Repositories linked to this paper

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

Abstract

In this paper we explore the recent topic of point cloud completion, guided by an auxiliary image. We show how it is possible to effectively combine the information from the two modalities in a localized latent space, thus avoiding the need for complex point cloud reconstruction methods from single views used by the state-of-the-art. We also investigate a novel weakly-supervised setting where the auxiliary image provides a supervisory signal to the training process by using a differentiable renderer on the completed point cloud to measure fidelity in the image space. Experiments show significant improvements over state-of-the-art supervised methods for both unimodal and multimodal completion. We also show the effectiveness of the weakly-supervised approach which outperforms a number of supervised methods and is competitive with the latest supervised models only exploiting point cloud information.

For agents

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

get_harvested_code_for_paper("2209.09552")
get_code_for_paper("2209.09552")
have("2209.09552")

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

curl https://syntology.ai/api/ran/2209.09552.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.09552.svg)](https://syntology.ai/paper/2209.09552)

Connect an agent — have() is free.