SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.19110 · CVPR · 2024

EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

Stavros Petridis, Maja Pantic, Zoe Landgraf, Antoni Bigata, Nikita Drobyshev, Casademunt Konstantinos Vougioukas

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 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/2404.19110.json · badge: /api/ran/2404.19110.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
neeek2303/EMOPortraits community
Papers with Code archive
6 ran · 1 no recorded run
FunctionStatusWhere it lives
ImportanceRenderer Ran
ran on a synthesized input · constructed an object; no result was computed
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("f8a173f407f1f5db")
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 an instance of its own class, ImportanceRenderer: the run constructed the object and did not call it, so no result was computed. 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 import nn

torch.manual_seed(0)

# Build a minimal decoder that matches how run_model uses it
class MinimalDecoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 4)  # 3 input coords, output rgb + sigma
    
    def forward(self, coordinates, features):
        # coordinates: (batch, num_rays, samples_per_ray, 3)
        # features: (batch, num_rays, samples_per_ray, C) or pass-through
        batch, rays, samples, _ = coordinates.shape
        coords_flat = coordinates.view(-1, 3)
        out_flat = self.linear(coords_flat)
        out = out_flat.view(batch, rays, samples, 4)
        return {
            'rgb': out[..., :3],    # (batch, rays, samples, 3)
            'sigma': out[..., 3:4]  # (batch, rays, samples, 1)
        }

decoder = MinimalDecoder()

# Build aligned_target_volume
# Expected shape from sample_from_features_all: (N, C, D, H, W)
batch_size = 2
aligned_target_volume = torch.randn(batch_size, 4, 8, 4, 4)

ARGS = {
    'depth_resolution': 5,
    'N_importance': 0
}
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 ImportanceRenderer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ImportanceRenderer 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
MipRayMarcher2 Ran
ran on a synthesized input
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("80b514efb4380504")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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 torch
import numpy as np

INIT_ARGS = {}

# MipRayMarcher2 expects:
# - colors: [batch, rays, samples, channels]
# - densities: [batch, rays, samples, 1]
# - depths: [batch, rays, samples, 1]

batch_size = 2
num_rays = 3
num_samples = 5
color_channels = 4

colors = torch.randn(batch_size, num_rays, num_samples, color_channels)
densities = torch.randn(batch_size, num_rays, num_samples, 1)
depths = torch.cumsum(torch.rand(batch_size, num_rays, num_samples, 1), dim=2)

ARGS = {
    'colors': colors,
    'densities': densities,
    'depths': depths
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
OSGDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("9fd052e5ad5901b0")
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 an instance of its own class, OSGDecoder: the run constructed the object and did not call it, so no result was computed. 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 import nn

torch.manual_seed(0)

ARGS = {
    'n_features': 16,
    'out_features': 3,
    'pos_encoding': False,
    'multires': 10,
    'features_sigm': 1,
    'squeeze_dim': 0,
    'depth_resolution': 48,
    'hidden_dim': 448,
    'num_layers': 2,
}
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 OSGDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a OSGDecoder 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
generate_planes Ran
ran on a synthesized input
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("b37c10c9de2f7e40")
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; 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

torch.manual_seed(0)

ARGS = {}
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 — no output shape is stated: observe_signature.py could not observe it (no_inputs)
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_embedder Ran
ran; our contract draft was wrong, not the code
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("a9f157f50bfdc4d5")
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
from torch import nn

torch.manual_seed(0)

# The function get_embedder takes two parameters: multires and i
# Based on the function body:
# - multires is used to compute max_freq_log2 and num_freqs
# - i is compared to -1 to determine which branch to take
# We'll test the main branch (i != -1) with typical values

ARGS = {
    'multires': 10,
    'i': 0
}
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 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
sample_from_features_all Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("8b88a2d7c9dc6ce7")
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 5, dtype family float, shape (2, 4, 3, 5, 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
import torch.nn as nn

torch.manual_seed(0)

# Construct features tensor: (N, C, D, H, W)
# N=2 (batch), C=4 (channels), D=3 (depth), H=5 (height), W=6 (width)
features = torch.randn(2, 4, 3, 5, 6)

# Construct coordinates tensor: (N, M, CD, 1)
# N=2 (batch), M=7 (number of points), CD=3 (coordinate dimensions)
coordinates = torch.randn(2, 7, 3, 1)

# Mode parameter - string for interpolation mode
mode = 'nearest'

# Padding mode parameter
padding_mode = 'zeros'

# Box warp parameter - None as default
box_warp = None

ARGS = {
    'features': features,
    'coordinates': coordinates,
    'mode': mode,
    'padding_mode': padding_mode,
    'box_warp': box_warp
}
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 5, dtype family float, shape (2, 4, 3, 5, 6) — shape (2, 4, 3, 5, 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
VolumeRenderer Not yet run
unverified (harvested, no recorded run)
neeek2303/EMOPortraits/networks/volumetric_avatar/volume_renderer.py
code served (permissive licence) · get_code("8bb13d64dd159959")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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.

For agents

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

get_harvested_code_for_paper("2404.19110")
get_code_for_paper("2404.19110")
have("2404.19110")

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

curl https://syntology.ai/api/ran/2404.19110.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.19110.svg)](https://syntology.ai/paper/2404.19110)

Connect an agent — have() is free.