SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.11291 · CVPR · 2024

Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption

Gim Lee, Liang Pan, Chen Li, Buzhen Huang, Chongyang Xu, Yangang Wang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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; 4 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/2404.11291.json · badge: /api/ran/2404.11291.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
boycehbz/humaninteraction canonical (classifier label)
classifier basis: census
4 ran · 4 no recorded run
FunctionStatusWhere it lives
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
boycehbz/humaninteraction/model/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from NVlabs/DiffPure, is pointer only (licence: NOASSERTION) · get_code("2ab2316ac6fdd869")
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 NVlabs/DiffPure, 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.

extract_into_tensor Ran
ran; our contract draft was wrong, not the code
boycehbz/humaninteraction/model/utils.py
code served (permissive licence) · get_code("221b8f4c28b8b95a")
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, shape (4, 1, 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
import numpy as np

torch.manual_seed(0)

# Create a 1-D numpy array to extract values from
arr = np.array([0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8], dtype=np.float32)

# Create a tensor of indices (timesteps) with batch size 2
timesteps = torch.tensor([0, 3, 1, 5], dtype=torch.long)

# Create a broadcast shape: [batch_size, 1, height, width]
# batch_size should match len(timesteps) = 4
broadcast_shape = (4, 1, 2, 3)

ARGS = {
    "arr": arr,
    "timesteps": timesteps,
    "broadcast_shape": broadcast_shape,
}
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 Tensor, ndim 4, dtype family float, shape (4, 1, 2, 3) — shape (4, 1, 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
extract_valid Ran
ran; our contract draft was wrong, not the code
boycehbz/humaninteraction/process.py
code served (permissive licence) · get_code("5c00afb233dd00ff")
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 dict. 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 numpy as np
import torch

torch.manual_seed(0)

batch_size = 2
frame_length = 3
agent_num = 4
num_vertices = 6
num_joints = 17

data = {
    'keypoints': np.random.randn(batch_size, frame_length, agent_num, 26, 3).astype(np.float32),
    'center': np.random.randn(batch_size, frame_length, agent_num, 2).astype(np.float32),
    'scale': np.random.randn(batch_size, frame_length, agent_num).astype(np.float32),
    'img_h': np.random.randn(batch_size, frame_length, agent_num).astype(np.float32),
    'img_w': np.random.randn(batch_size, frame_length, agent_num).astype(np.float32),
    'focal_length': np.random.randn(batch_size, frame_length, agent_num).astype(np.float32),
    'valid': np.random.randint(0, 2, (batch_size, frame_length, agent_num)).astype(np.float32),
    'has_3d': np.random.randint(0, 2, (batch_size, frame_length, agent_num, 1)).astype(np.float32),
    'has_smpl': np.random.randint(0, 2, (batch_size, frame_length, agent_num, 1)).astype(np.float32),
    'verts': np.random.randn(batch_size, frame_length, agent_num, num_vertices, 3).astype(np.float32),
    'gt_joints': np.random.randn(batch_size, frame_length, agent_num, num_joints, 4).astype(np.float32),
    'pose': np.random.randn(batch_size, frame_length, agent_num, 72).astype(np.float32),
    'betas': np.random.randn(batch_size, frame_length, agent_num, 10).astype(np.float32),
    'gt_cam_t': np.random.randn(batch_size, frame_length, agent_num, 3).astype(np.float32),
    'imgname': np.array([['img_001', 'img_002', 'img_003'],
                         ['img_004', 'img_005', 'img_006']]),
}

ARGS = {
    'data': data
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
set_seed Ran
ran; our contract draft was wrong, not the code
boycehbz/humaninteraction/utils/module_utils.py
code served (permissive licence) · get_code("605781546526fa77")
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 Generator. 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 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
import random
import torch

torch.manual_seed(0)

ARGS = {
    "seed": 42
}
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 Generator — a Generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Generator 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
extract_valid_demo Not yet run
unverified (harvested, no recorded run)
boycehbz/humaninteraction/process.py
code served (permissive licence) · get_code("cf9b30544b2674f8")
How it ran

no invocation recorded.

get_named_beta_schedule Not yet run
unverified (harvested, no recorded run)
boycehbz/humaninteraction/model/utils.py
code served (permissive licence) · get_code("cf1961ab8022ee7b")
How it ran

no invocation recorded.

load_camera_para Not yet run
unverified (harvested, no recorded run)
boycehbz/humaninteraction/utils/module_utils.py
code served (permissive licence) · get_code("b8519581787b874c")
How it ran

no invocation recorded.

merge_gt Not yet run
unverified (harvested, no recorded run)
boycehbz/humaninteraction/process.py
code served (permissive licence) · get_code("8e710153600ef95e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 6 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
betas_for_alpha_bar 92 other papers
67 dated earlier, 3 the same month, 20 later, 2 same year, order not determinable · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
and 89 more not named here
get_named_beta_schedule 63 other papers
42 dated earlier, 2 the same month, 18 later, 1 same year, order not determinable
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2108.02938 (2021-08)
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 60 more not named here

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

Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration, but overlook the modeling of close interactions. In this work, we tackle the task of reconstructing closely interactive humans from a monocular video. The main challenge of this task comes from insufficient visual information caused by depth ambiguity and severe inter-person occlusion. In view of this, we propose to leverage knowledge from proxemic behavior and physics to compensate the lack of visual information. This is based on the observation that human interaction has specific patterns following the social proxemics. Specifically, we first design a latent representation based on Vector Quantised-Variational AutoEncoder (VQ-VAE) to model human interaction. A proxemics and physics guided diffusion model is then introduced to denoise the initial distribution. We design the diffusion model as dual branch with each branch representing one individual such that the interaction can be modeled via cross attention. With the learned priors of VQ-VAE and physical constraint as the additional information, our proposed approach is capable of estimating accurate poses that are also proxemics and physics plausible. Experimental results on Hi4D, 3DPW, and CHI3D demonstrate that our method outperforms existing approaches. The code is available at https://github.com/boycehbz/ HumanInteraction.

For agents

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

get_harvested_code_for_paper("2404.11291")
get_code_for_paper("2404.11291")
have("2404.11291")

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

curl https://syntology.ai/api/ran/2404.11291.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.11291.svg)](https://syntology.ai/paper/2404.11291)

Connect an agent — have() is free.