SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.17346 · ECCV · 2024

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Kostas Daniilidis, Lingjie Liu, Ziyun Wang, Yufu Wang

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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; 6 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 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/2403.17346.json · badge: /api/ran/2403.17346.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
yufu-wang/tram canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
cam_wrt_gravity Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/camera/est_gravity.py
code served (permissive licence) · get_code("f97f0472c6ce0b65")
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 (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 torch
import math

torch.manual_seed(0)

# The function cam_wrt_gravity takes two parameters: pitch and roll
# Both are angles (floats) used in trigonometric operations
# Let's create reasonable angle values in radians

pitch = math.pi / 6  # 30 degrees
roll = math.pi / 4   # 45 degrees

ARGS = {
    "pitch": pitch,
    "roll": roll,
}
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 (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
cam_wrt_world Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/camera/est_gravity.py
code served (permissive licence) · get_code("51f1f7730e448854")
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 (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 math
import torch

torch.manual_seed(0)

# The function cam_wrt_world takes pitch and roll as parameters
# Looking at the function body:
# - pitch is passed to cam_wrt_gravity, which passes it to rotation_about_x
# - roll is passed to cam_wrt_gravity, which passes it to rotation_about_y
# - rotation_about_x and rotation_about_y expect float angles
# So pitch and roll should be float values (angles in radians)

pitch = 0.5  # angle in radians
roll = 0.3   # angle in radians

ARGS = {
    "pitch": pitch,
    "roll": roll
}
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 (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
compute_l2_loss Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/core/losses.py
code served (permissive licence) · get_code("47e67073b5581024")
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
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects a batch dict with 'x2' and 'output' keys
# Both should be tensors that can be compared with F.mse_loss
batch = {
    'x2': torch.randn(2, 4),      # batch size 2, dimension 4
    'output': torch.randn(2, 4)   # batch size 2, dimension 4
}

ARGS = {
    'batch': 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 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
est_calib Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/camera/slam_utils.py
code served (permissive licence) · get_code("2dcee438683ee8a4")
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 list, 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 tempfile
import os
import cv2
import numpy as np

# Create a temporary directory with a test image
tmpdir = tempfile.mkdtemp()
test_image = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
cv2.imwrite(os.path.join(tmpdir, 'test.jpg'), test_image)

ARGS = {
    'imagedir': tmpdir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
est_scale_gmof Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yufu-wang/tram/lib/camera/est_scale.py
code served (permissive licence) · get_code("e4c8b52fda09392f")
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 float, 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 numpy as np
import cv2
import torch

torch.manual_seed(0)

# Create small depth maps (height=4, width=3)
slam_depth = np.random.uniform(1, 5, size=(4, 3)).astype(np.float32)
pred_depth = np.random.uniform(1, 5, size=(4, 3)).astype(np.float32)

# Create a small mask (height=2, width=2) to test resizing
msk = np.random.uniform(0, 1, size=(2, 2)).astype(np.float32)

ARGS = {
    "slam_depth": slam_depth,
    "pred_depth": pred_depth,
    "lr": 0.01,
    "sigma": 0.5,
    "iters": 10,
    "msk": msk,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
est_scale_iterative Ran
ran on a synthesized input
yufu-wang/tram/lib/camera/est_scale.py
code served (permissive licence) · get_code("43f07fe60d9771d9")
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 float32, 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 numpy as np
import cv2

# Create small depth maps with distinct dimensions
slam_depth = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [1.5, 2.5, 3.5, 4.5],
    [2.0, 3.0, 4.0, 5.0]
], dtype=np.float32)

pred_depth = np.array([
    [2.0, 4.0, 6.0, 8.0],
    [3.0, 5.0, 7.0, 9.0],
    [4.0, 6.0, 8.0, 10.0]
], dtype=np.float32)

# Create a mask with shape that will be resized to match pred_depth
msk = np.array([
    [0.0, 0.1, 0.2, 0.3],
    [0.1, 0.2, 0.3, 0.4]
], dtype=np.float32)

ARGS = {
    "slam_depth": slam_depth,
    "pred_depth": pred_depth,
    "iters": 5,
    "msk": msk
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, 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
get_dimention Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/camera/slam_utils.py
code served (permissive licence) · get_code("3d45d8fea0a6ba6f")
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 int; 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 numpy as np
import cv2
import tempfile
import os

# Create a temporary directory with a test image
tmpdir = tempfile.mkdtemp()
test_image = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
cv2.imwrite(os.path.join(tmpdir, 'test.jpg'), test_image)

ARGS = {
    'imagedir': tmpdir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 int — 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_lr_cycle_scheduler Ran
ran; our contract draft was wrong, not the code
yufu-wang/tram/lib/core/base_trainer.py
code served (permissive licence) · get_code("9b09946e117bbab5")
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 OneCycleLR. 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 simple model with parameters
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# Define ARGS dict with all parameters
ARGS = {
    'optimizer': optimizer,
    'total_steps': 50000
}
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 OneCycleLR — a OneCycleLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OneCycleLR 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_lr_scheduler Ran
ran; our contract draft was wrong, not the code
yufu-wang/tram/lib/core/base_trainer.py
code served (permissive licence) · get_code("9b438214a4dff91b")
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

torch.manual_seed(0)

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

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# Define the arguments
ARGS = {
    'optimizer': optimizer,
    'warmup_steps': 10,
    'schedule': [20, 40, 60],
    'decay': 0.1
}
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
keypoint_loss Ran
ran, honoured the contract we drafted
yufu-wang/tram/lib/core/losses.py
code served (permissive licence) · get_code("ddd90785d243b136")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create batch dictionary with required tensors
# pred_keypoints_2d: predicted 2D keypoints without confidence
# keypoints: ground truth 2D keypoints with confidence as last dimension
batch_size = 2
num_keypoints = 50
keypoint_dim = 2

# pred_keypoints_2d shape: (batch_size, num_keypoints, keypoint_dim)
pred_keypoints_2d = torch.randn(batch_size, num_keypoints, keypoint_dim)

# keypoints shape: (batch_size, num_keypoints, keypoint_dim + 1)
# Last dimension is confidence score
keypoints = torch.randn(batch_size, num_keypoints, keypoint_dim + 1)
# Set confidence values to be between 0 and 1
keypoints[:, :, -1] = torch.rand(batch_size, num_keypoints)

batch = {
    'pred_keypoints_2d': pred_keypoints_2d,
    'keypoints': keypoints
}

ARGS = {
    'batch': batch,
    'openpose_weight': 0.5,
    'gt_weight': 1.0
}
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 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
parse_args Ran
ran; our contract draft was wrong, not the code
yufu-wang/tram/lib/core/config.py
code served (permissive licence) · get_code("8a1791646b3bf7ea")
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 CfgNode. 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 tempfile
import os
from yacs.config import CfgNode as CN

# Create a minimal config file for testing
config_content = """
MODEL:
  NAME: "test_model"
  HIDDEN_DIM: 128
TRAIN:
  LR: 0.001
  EPOCHS: 10
"""

# Write config to a temporary file
temp_dir = tempfile.gettempdir()
cfg_file_path = os.path.join(temp_dir, "test_config.yaml")
with open(cfg_file_path, "w") as f:
    f.write(config_content)

# Define ARGS mapping all parameters of parse_args
ARGS = {
    'args': ['--cfg', cfg_file_path]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
preprocess_masks Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yufu-wang/tram/lib/camera/slam_utils.py
code served (permissive licence) · get_code("87f90af29b982adb")
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 torch
import tempfile
import os
import cv2
import numpy as np

torch.manual_seed(0)

# Create a temporary directory with a dummy jpg file
tmpdir = tempfile.mkdtemp()
dummy_image = np.random.randint(0, 255, (100, 120, 3), dtype=np.uint8)
jpg_path = os.path.join(tmpdir, "image_0.jpg")
cv2.imwrite(jpg_path, dummy_image)

# Create masks tensor with shape (batch_size, channels, height, width)
# Using small dimensions: 2 masks, 1 channel, 4x6 resolution
masks = torch.randn(2, 1, 4, 6)

ARGS = {
    "img_folder": tmpdir,
    "masks": masks,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch, torchvision — 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
update_cfg Ran
ran; our contract draft was wrong, not the code
yufu-wang/tram/lib/core/config.py
code served (permissive licence) · get_code("8cae4a5d48fbd269")
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 CfgNode. 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
from yacs.config import CfgNode as CN

# Create a temporary config file for testing
temp_dir = tempfile.mkdtemp()
cfg_file = os.path.join(temp_dir, "config.yaml")

# Write a minimal valid YAML config file
with open(cfg_file, 'w') as f:
    f.write("MODEL:\n")
    f.write("  NAME: test_model\n")
    f.write("TRAIN:\n")
    f.write("  LR: 0.001\n")

ARGS = {
    'cfg_file': cfg_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
keypoint_3d_loss Not yet run
unverified (harvested, no recorded run)
yufu-wang/tram/lib/core/losses.py
code served (permissive licence) · get_code("df63348c72c98591")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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.

Abstract

We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presence of dynamic humans and uses the scene background to derive the motion scale. Using the recovered camera as a metric-scale reference frame, we introduce a video transformer model (VIMO) to regress the kinematic body motion of a human. By composing the two motions, we achieve accurate recovery of 3D humans in the world space, reducing global motion errors by a large margin from prior work. https://yufu-wang.github.io/tram4d/ Fig. 1: Overview. Given an in-the-wild video, TRAM reconstructs the complete 3D human motion: global trajectory and local body motion, in diverse and longrange scenarios.

For agents

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

get_harvested_code_for_paper("2403.17346")
get_code_for_paper("2403.17346")
have("2403.17346")

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

curl https://syntology.ai/api/ran/2403.17346.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.17346.svg)](https://syntology.ai/paper/2403.17346)

Connect an agent — have() is free.