SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.08503 · ICLR · 2024

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis

Yi Ren, Zhou Zhao, Chen Zhang, Jinglin Liu, Jiawei Huang, Rongjie Huang, Jinzheng He, Jiaqi Yang, Zhenhui Ye, Ziyue Jiang, Yin Zejun, Tianyun Zhong, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 1 has no contract verdict; 3 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/2401.08503.json · badge: /api/ran/2401.08503.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
yerfor/Real3DPortrait canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
filter_state_dict Ran
ran; our contract draft was wrong, not the code
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/networks.py
code served (permissive licence) · get_code("0f6c5532e66c554c")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a sample state dict that mimics a model's state_dict()
# This would typically come from torch.load() or model.state_dict()
state_dict = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'fc.weight': torch.randn(2, 4),
    'fc.bias': torch.randn(2),
    'layer2.weight': torch.randn(5, 4),
    'layer2.bias': torch.randn(5),
}

ARGS = {
    'state_dict': state_dict,
    'remove_name': 'fc'
}
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 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
get_scheduler Ran
ran; our contract draft was wrong, not the code
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/networks.py
code served (permissive licence) · get_code("962cf09d55becbb1")
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 LambdaLR. 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 torch.nn as nn
from torch.optim import Adam

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = Adam(model.parameters(), lr=0.001)

# Create a minimal options class with all required attributes
class BaseOptions:
    pass

opt = BaseOptions()
opt.lr_policy = 'linear'
opt.epoch_count = 0
opt.n_epochs = 10

ARGS = {
    'optimizer': optimizer,
    'opt': opt
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
perceptual_loss Ran
ran; our contract draft was wrong, not the code
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/losses.py
code served (permissive licence) · get_code("945b4307eb32c770")
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 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 torch

torch.manual_seed(0)

# The function expects two tensors of feature vectors
# It computes cosine similarity along the last dimension
# and returns a scalar loss

# Create two feature tensors with shape (batch_size, feature_dim)
# batch_size = 2, feature_dim = 4
id_featureA = torch.randn(2, 4)
id_featureB = torch.randn(2, 4)

ARGS = {
    "id_featureA": id_featureA,
    "id_featureB": id_featureB,
}
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 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
perspective_projection Ran
ran, honoured the contract we drafted
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/bfm.py
code served (permissive licence) · get_code("2e9ce6a02832f7c8")
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 ndarray, ndim 2, dtype family float, shape (3, 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 numpy as np

# The function perspective_projection takes two parameters: focal and center
# Looking at the function body:
# - focal is used in np.array as a scalar value (appears twice in the array)
# - center is used in np.array as a scalar value (appears twice in the array)
# - Both are used to construct a 3x3 matrix for perspective projection

# Create small float values for focal length and image center coordinate
focal = 500.0
center = 320.0

ARGS = {
    "focal": focal,
    "center": center
}
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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
photo_loss Ran
ran on a synthesized input
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/losses.py
code served (permissive licence) · get_code("8ee1568e301607cf")
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 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 torch

torch.manual_seed(0)

# Create small image tensors: (B=2, C=3, H=4, W=5)
# Range (0, 1), RGB order
imageA = torch.rand(2, 3, 4, 5)
imageB = torch.rand(2, 3, 4, 5)

# Create mask tensor: (B=2, 1, H=4, W=5)
# Values between 0 and 1 to indicate valid regions
mask = torch.rand(2, 1, 4, 5)

# eps parameter for numerical stability
eps = 1e-06

ARGS = {
    "imageA": imageA,
    "imageB": imageB,
    "mask": mask,
    "eps": eps,
}
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 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
resize_n_crop Not yet run
unverified (harvested, no recorded run)
yerfor/Real3DPortrait/deep_3drecon/deep_3drecon_models/losses.py
code served (permissive licence) · get_code("2870025ec65fec68")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
filter_state_dict 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Wang_3D_Face_Reconstruction_with_the_Geometric_Guidance_of_Facial_Part_CVPR_2024_paper (2024 (year only))
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
2408.09458 (2024-08)
G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
perspective_projection 3 other papers
2 dated earlier, 1 later
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
2301.13430 (2023-01)
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis
2408.09458 (2024-08)
G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
resize_n_crop 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Wang_3D_Face_Reconstruction_with_the_Geometric_Guidance_of_Facial_Part_CVPR_2024_paper (2024 (year only))
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
2408.09458 (2024-08)
G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
get_scheduler 2 other papers
1 dated earlier, 1 same year, order not determinable
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Wang_3D_Face_Reconstruction_with_the_Geometric_Guidance_of_Facial_Part_CVPR_2024_paper (2024 (year only))
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
perceptual_loss 1 other paper
1 dated earlier
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
photo_loss 1 other paper
1 dated earlier
1903.08527 (2019-03)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

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

One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talking face animation. Besides, while the existing works mainly focus on synthesizing the head part, it is also vital to generate natural torso and background segments to obtain a realistic talking portrait video. To address these limitations, we present Real3D-Potrait, a framework that (1) improves the one-shot 3D reconstruction power with a large image-to-plane model that distills 3D prior knowledge from a 3D face generative model; (2) facilitates accurate motion-conditioned animation with an efficient motion adapter; (3) synthesizes realistic video with natural torso movement and switchable background using a head-torso-background super-resolution model; and (4) supports one-shot audio-driven talking face generation with a generalizable audio-to-motion model. Extensive experiments show that Real3D-Portrait generalizes well to unseen identities and generates more realistic talking portrait videos compared to previous methods 1 .

For agents

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

get_harvested_code_for_paper("2401.08503")
get_code_for_paper("2401.08503")
have("2401.08503")

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

curl https://syntology.ai/api/ran/2401.08503.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.08503.svg)](https://syntology.ai/paper/2401.08503)

Connect an agent — have() is free.