SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.14402 · 2022

UV Volumes for Real-time Rendering of Editable Free-view Human Performance

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 2 have no contract verdict; 2 failures of our instrument; 1 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/2203.14402.json · badge: /api/ran/2203.14402.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
fanegg/UV-Volumes canonical (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
get_embedder Ran
ran; our contract draft was wrong, not the code
fanegg/UV-Volumes/lib/networks/embedder.py
pointer only (licence: MIT); the stored copy get_code serves, from isee-laboratory/rogsplat, is pointer only (licence: NONE) · get_code("23a994dc4b638c73")
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 isee-laboratory/rogsplat, 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.

make_collator Ran
ran on a synthesized input
fanegg/UV-Volumes/lib/datasets/collate_batch.py
code served (permissive licence) · get_code("f8c8c131e2535539")
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 function. 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
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.train = MockCollatorConfig()
        self.test = MockCollatorConfig()

class MockCollatorConfig:
    def __init__(self):
        self.collator = "default"

# Test case 1: collator in _collators
_collators = {}

cfg1 = MockConfig()
cfg1.train.collator = "custom_collator"
cfg1.test.collator = "default"

ARGS = {
    "cfg": cfg1,
    "is_train": True
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
make_evaluator Ran
ran; our contract draft was wrong, not the code
fanegg/UV-Volumes/lib/evaluators/make_evaluator.py
code served (permissive licence) · get_code("b0c00209a1cb4ff9")
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 Evaluator. 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 tempfile
import os

# Create a minimal evaluator module to be loaded
evaluator_code = '''
class Evaluator:
    def __init__(self):
        pass
'''

# Write the evaluator module to a temporary file
temp_dir = tempfile.mkdtemp()
evaluator_path = os.path.join(temp_dir, 'evaluator_module.py')
with open(evaluator_path, 'w') as f:
    f.write(evaluator_code)

# Create a config object with the required attributes
class Config:
    def __init__(self):
        self.skip_eval = False
        self.evaluator_module = 'evaluator_module'
        self.evaluator_path = evaluator_path

ARGS = {
    'cfg': Config()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
imp — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Evaluator — a Evaluator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Evaluator 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
make_transforms Ran
ran on a synthesized input
fanegg/UV-Volumes/lib/datasets/transforms.py
code served (permissive licence) · get_code("c3d191e87fdb12ac")
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 Compose. 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

torch.manual_seed(0)

class Config:
    pass

cfg = Config()

is_train = True

ARGS = {
    'cfg': cfg,
    'is_train': is_train
}
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 Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
load_cfg Not yet run
unverified (harvested, no recorded run)
fanegg/UV-Volumes/lib/config/yacs.py
code served (permissive licence) · get_code("97bdde621f4f33ec")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 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
get_embedder 2 other papers
2 later
2312.02973 (2023-12)
GauHuman: Articulated Gaussian Splatting from Monocular Human Videos
2503.14198 (2025-03)
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
load_cfg 2 other papers
2 later
2310.08585 (2023-10)
Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes
2405.12218 (2024-05)
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
make_evaluator 1 other paper
1 later
2405.12218 (2024-05)
MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

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

Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications. But the practice is severely limited by high computational costs in the rendering process. To solve this problem, we propose the UV Volumes, a new approach that can render an editable free-view video of a human performer in real-time. It separates the high-frequency (i.e., non-smooth) human appearance from the 3D volume, and encodes them into 2D neural texture stacks (NTS). The smooth UV volumes allow much smaller and shallower neural networks to obtain densities and texture coordinates in 3D while capturing detailed appearance in 2D NTS. For editability, the mapping between the parameterized human model and the smooth texture coordinates allows us a better generalization on novel poses and shapes. Furthermore, the use of NTS enables interesting applications, e.g., retexturing. Extensive experiments on CMU Panoptic, ZJU Mocap, and H36M datasets show that our model can render 960 x 540 images in 30FPS on average with comparable photo-realism to state-of-the-art methods. The project and supplementary materials are available at https://fanegg.github.io/UV-Volumes.

For agents

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

get_harvested_code_for_paper("2203.14402")
get_code_for_paper("2203.14402")
have("2203.14402")

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

curl https://syntology.ai/api/ran/2203.14402.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.14402.svg)](https://syntology.ai/paper/2203.14402)

Connect an agent — have() is free.