SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.05570 · 2020

PLACE: Proximity Learning of Articulation and Contact in 3D Environments

arXiv · PDF · Open in the Atlas

Code that ran

6 of 12 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 4 have no contract verdict; 2 failures of our instrument; 6 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/2008.05570.json · badge: /api/ran/2008.05570.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
sanweiliti/PLACE canonical (classifier label)
classifier basis: census
6 ran · 6 no recorded run
FunctionStatusWhere it lives
blend_shapes Ran
ran; our contract draft was wrong, not the code
sanweiliti/PLACE/human_body_prior/body_model/lbs.py
pointer only (licence: MIT); the stored copy get_code serves, from apple/ml-neuman, is pointer only (licence: NOASSERTION) · get_code("9cc3777ffe0040d2")
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 apple/ml-neuman, 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.

define_scene_boundary Ran
ran on a synthesized input
sanweiliti/PLACE/utils_read_data.py
code served (permissive licence) · get_code("ca76bb791dcba2b1")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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
import numpy as np

torch.manual_seed(0)

# The function define_scene_boundary takes two parameters:
# 1. dataset: a string that can be 'prox', 'mp3d', or 'replica'
# 2. scene_name: a string that matches one of the valid scene names for the dataset

# We'll test with a valid combination from the 'prox' dataset
ARGS = {
    'dataset': 'prox',
    'scene_name': 'MPH1Library'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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_contact_id Ran
ran on a synthesized input
sanweiliti/PLACE/utils.py
code served (permissive licence) · get_code("14dc3e468cac5d42")
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 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 sys
import os
import json
import tempfile
import numpy as np

# Create a temporary directory to hold the JSON files
temp_dir = tempfile.mkdtemp()

# Create sample JSON files for the contact body parts
contact_body_parts = ['L_Hand', 'R_Hand']

for part in contact_body_parts:
    data = {
        'verts_ind': [0, 1, 2, 3, 4, 5, 1, 2],  # Some indices with duplicates
        'faces_ind': [10, 11, 12, 13, 11, 12]   # Some indices with duplicates
    }
    filepath = os.path.join(temp_dir, part + '.json')
    with open(filepath, 'w') as f:
        json.dump(data, f)

# Define ARGS
ARGS = {
    'body_segments_folder': temp_dir,
    'contact_body_parts': ['L_Hand', 'R_Hand']
}
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 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
normalize_global_T Ran
ran on a synthesized input
sanweiliti/PLACE/utils.py
code served (permissive licence) · get_code("d88e586e5bcd6b52")
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, 7) 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_batch: shape [batch_size, feature_dim] where first 3 are translation, rest are rotation/local params
batch_size = 2
translation_dim = 3
rotation_local_dim = 4
x_batch = torch.randn(batch_size, translation_dim + rotation_local_dim)

# cam_intrinsic: shape [batch_size, 3, 3] camera intrinsic matrix
# Need fx, fy at [0,0] and [1,1], px, py at [0,2] and [1,2]
cam_intrinsic = torch.zeros(batch_size, 3, 3)
cam_intrinsic[:, 0, 0] = torch.tensor([500.0, 510.0])  # fx values
cam_intrinsic[:, 1, 1] = torch.tensor([500.0, 510.0])  # fy values
cam_intrinsic[:, 0, 2] = torch.tensor([320.0, 330.0])  # px values
cam_intrinsic[:, 1, 2] = torch.tensor([240.0, 250.0])  # py values
cam_intrinsic[:, 2, 2] = 1.0

# max_depth: scalar float for depth normalization
max_depth = 10.0

ARGS = {
    "x_batch": x_batch,
    "cam_intrisic": cam_intrinsic,
    "max_depth": max_depth,
}
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, 7) — shape (2, 7) 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
vertices2joints Ran
ran; our contract draft was wrong, not the code
sanweiliti/PLACE/human_body_prior/body_model/lbs.py
pointer only (licence: MIT); the stored copy get_code serves, from apple/ml-neuman, is pointer only (licence: NOASSERTION) · get_code("6785daa25845e4be")
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 apple/ml-neuman, 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.

verts_transform Ran
ran on a synthesized input
sanweiliti/PLACE/utils.py
code served (permissive licence) · get_code("7b82953c45836e03")
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, 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)

# verts_batch: batch of vertices, shape (batch_size, num_verts, 3)
# cam_ext_batch: camera extrinsic matrices, shape (batch_size, 4, 4)

batch_size = 2
num_verts = 4
verts_batch = torch.randn(batch_size, num_verts, 3)

# Camera extrinsic matrix: 4x4 transformation matrix
cam_ext_batch = torch.randn(batch_size, 4, 4)

ARGS = {
    'verts_batch': verts_batch,
    'cam_ext_batch': cam_ext_batch,
}
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, 3) — shape (2, 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
NN_loss Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/chamfer_pytorch/chamfer_python.py
pointer only (licence: MIT); the stored copy get_code serves, from Forrest-110/FluidMotionNet, is pointer only (licence: GPL-3.0) · get_code("d5fe9376d02c3c68")
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 Forrest-110/FluidMotionNet, and GPL-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. No invocation recorded.

distChamfer Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/chamfer_pytorch/chamfer_python.py
code served (permissive licence) · get_code("a51f13880992b880")
How it ran

no invocation recorded.

diversity Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/eval_diversity.py
code served (permissive licence) · get_code("1adf819eec0a0b9a")
How it ran

no invocation recorded.

get Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/chamfer_pytorch/get_chamfer.py
code served (permissive licence) · get_code("a947f54a81b11553")
How it ran

no invocation recorded.

lbs Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/human_body_prior/body_model/lbs.py
code served (permissive licence) · get_code("5d3e7dc328302eae")
How it ran

no invocation recorded.

pairwise_dist Not yet run
unverified (harvested, no recorded run)
sanweiliti/PLACE/chamfer_pytorch/chamfer_python.py
pointer only (licence: MIT); the stored copy get_code serves, from Forrest-110/FluidMotionNet, is pointer only (licence: GPL-3.0) · get_code("b36f714d8eb76c94")
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 Forrest-110/FluidMotionNet, and GPL-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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 8 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
NN_loss 1 other paper
1 later
2410.11934 (2024-10)
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
blend_shapes 1 other paper
1 later
2203.12575 (2022-03)
NeuMan: Neural Human Radiance Field from a Single Video
pairwise_dist 1 other paper
1 later
2410.11934 (2024-10)
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
vertices2joints 1 other paper
1 later
2203.12575 (2022-03)
NeuMan: Neural Human Radiance Field from a Single Video

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

High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps to represent the scene, and parametric human models to represent 3D bodies. While being straightforward, their generated human-scene interactions are often lack of naturalness and physical plausibility. Our key observation is that humans interact with the world through body-scene contact. To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world. To that end, we propose a novel interaction generation method, named PLACE (Proximity Learning of Articulation and Contact in 3D Environments), which explicitly models the proximity between the human body and the 3D scene around it. Specifically, given a set of basis points on a scene mesh, we leverage a conditional variational autoencoder to synthesize the minimum distances from the basis points to the human body surface. The generated proximal relationship exhibits which region of the scene is in contact with the person. Furthermore, based on such synthesized proximity, we are able to effectively obtain expressive 3D human bodies that interact with the 3D scene naturally. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction. We believe our method makes an important step towards the fully automatic synthesis of realistic 3D human bodies in 3D scenes. The code and model are available for research at https://sanweiliti.github.io/PLACE/PLACE.html.

For agents

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

get_harvested_code_for_paper("2008.05570")
get_code_for_paper("2008.05570")
have("2008.05570")

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

curl https://syntology.ai/api/ran/2008.05570.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.05570.svg)](https://syntology.ai/paper/2008.05570)

Connect an agent — have() is free.