SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.12462 · 2021

Points2Sound: From mono to binaural audio using 3D point cloud scenes

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 0 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/2104.12462.json · badge: /api/ran/2104.12462.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
francesclluis/points2sound canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Envelope_distance Ran
ran, honoured the contract we drafted
francesclluis/points2sound/metrics_binaural.py
code served (permissive licence) · get_code("6dd7d61d18bfaea5")
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 float, ndim 0, dtype family float, shape () 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
from scipy.signal import hilbert

# Create two 2D arrays representing binaural audio
# Shape: (2 channels, 100 samples)
predicted_binaural = np.random.randn(2, 100).astype(np.float32)
gt_binaural = np.random.randn(2, 100).astype(np.float32)

ARGS = {
    "predicted_binaural": predicted_binaural,
    "gt_binaural": gt_binaural,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
center_trim Ran
ran; our contract draft was wrong, not the code
francesclluis/points2sound/models/audio_net.py
code served (permissive licence) · get_code("03ce5ded167a28fd")
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, 4, 6) 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 center_trim trims a tensor symmetrically around its center
# based on a reference size. It checks for a 'size' attribute on reference,
# or uses reference directly as an integer.

# tensor: needs to have size(-1) method and support slicing
# reference: can be either an object with size(-1) method, or an integer

tensor = torch.randn(2, 4, 10)  # shape (2, 4, 10), last dim is 10
reference = torch.randn(2, 4, 6)  # shape (2, 4, 6), last dim is 6 (smaller than tensor's last dim)

ARGS = {
    "tensor": tensor,
    "reference": reference
}
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, 4, 6) — shape (2, 4, 6) 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
unet_conv Ran
ran; our contract draft was wrong, not the code
francesclluis/points2sound/models/audio_net.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/visualvoice, is pointer only (licence: NOASSERTION) · get_code("c26dd101957c5772")
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 facebookresearch/visualvoice, and GitHub could not classify the licence of that repository (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.

unet_upconv Ran
ran; our contract draft was wrong, not the code
francesclluis/points2sound/models/audio_net.py
pointer only (licence: MIT); the stored copy get_code serves, from merlresearch/AVSGS, is pointer only (licence: AGPL-3.0) · get_code("e1be3fb442f83f7f")
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 merlresearch/AVSGS, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
unet_conv 2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
2101.03149 (2021-01)
VISUALVOICE: Audio-Visual Speech Separation with Cross-Modal Consistency
2109.11955 (2021-09)
Visual Scene Graphs for Audio Source Separation
center_trim 1 other paper
1 dated earlier
2010.06007 (2020-10)
The Cone of Silence: Speech Separation by Localization
unet_upconv 1 other paper
1 later
2109.11955 (2021-09)
Visual Scene Graphs for Audio Source Separation

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

For immersive applications, the generation of binaural sound that matches its visual counterpart is crucial to bring meaningful experiences to people in a virtual environment. Recent studies have shown the possibility of using neural networks for synthesizing binaural audio from mono audio by using 2D visual information as guidance. Extending this approach by guiding the audio with 3D visual information and operating in the waveform domain may allow for a more accurate auralization of a virtual audio scene. We propose Points2Sound, a multi-modal deep learning model which generates a binaural version from mono audio using 3D point cloud scenes. Specifically, Points2Sound consists of a vision network and an audio network. The vision network uses 3D sparse convolutions to extract a visual feature from the point cloud scene. Then, the visual feature conditions the audio network, which operates in the waveform domain, to synthesize the binaural version. Results show that 3D visual information can successfully guide multi-modal deep learning models for the task of binaural synthesis. We also investigate how 3D point cloud attributes, learning objectives, different reverberant conditions, and several types of mono mixture signals affect the binaural audio synthesis performance of Points2Sound for the different numbers of sound sources present in the scene.

For agents

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

get_harvested_code_for_paper("2104.12462")
get_code_for_paper("2104.12462")
have("2104.12462")

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

curl https://syntology.ai/api/ran/2104.12462.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.12462.svg)](https://syntology.ai/paper/2104.12462)

Connect an agent — have() is free.