SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.15055 · ICCV · 2023

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

Leonidas Guibas, Gordon Wetzstein, Yang Zheng, Adam Harley, Bokui Shen

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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; 4 honoured the contract we drafted, 0 violated it and 2 have 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/2307.15055.json · badge: /api/ran/2307.15055.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
y-zheng18/point_odyssey canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
aharley/pips2 community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
aliciachenw/PIPsUS extension (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
as_path Ran
ran; our contract draft was wrong, not the code
y-zheng18/point_odyssey/utils/file_io.py
pointer only (licence: NOASSERTION) · get_code("2cb7740d09d1d57c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

coords_grid Ran
ran, honoured the contract we drafted
aliciachenw/PIPsUS/nets/pipsUS.py
code served (permissive licence) · get_code("ea43be6c224959b1")
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) and returned Tensor, ndim 4, dtype family float, shape (2, 2, 4, 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

torch.manual_seed(0)

ARGS = {
    "batch": 2,
    "ht": 4,
    "wd": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (2, 2, 4, 3) — shape (2, 2, 4, 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
farthest_point_sampling Ran
ran; our contract draft was wrong, not the code
y-zheng18/point_odyssey/utils/gen_tracking.py
pointer only (licence: NOASSERTION) · get_code("b360fe44d7520e4a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

fetch_optimizer Ran
ran on a synthesized input
aharley/pips2/finetune_highres.py
code served (permissive licence) · get_code("257df3eb14fc528b")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small model with parameters
class TinyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = TinyModel()

ARGS = {
    'lr': 0.001,
    'wdecay': 0.01,
    'epsilon': 1e-8,
    'num_steps': 100,
    'params': model.parameters()
}
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
get_calibration_matrix_K_from_blender Ran
ran, honoured the contract we drafted
y-zheng18/point_odyssey/render_animal.py
pointer only (licence: NOASSERTION) · get_code("4f778b5ed0da9d1f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

get_intrinsics Ran
ran, honoured the contract we drafted
y-zheng18/point_odyssey/render_single.py
pointer only (licence: NOASSERTION) · get_code("0bc392e72f43660f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

load Ran
ran, honoured the contract we drafted
aharley/pips2/saverloader.py
code served (permissive licence) · get_code("7cc0ed613ecce873")
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 int, ndim 0, dtype family int, 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 as nn
import tempfile
import os

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal optimizer
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a minimal scheduler
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=1)

# Create a temporary checkpoint directory with a valid checkpoint file
ckpt_dir = tempfile.mkdtemp()

# Create a checkpoint file
checkpoint = {
    'model_state_dict': model.state_dict(),
    'optimizer_state_dict': optimizer.state_dict(),
    'scheduler_state_dict': scheduler.state_dict()
}
ckpt_path = os.path.join(ckpt_dir, 'model-000000001.pth')
torch.save(checkpoint, ckpt_path)

# Define arguments
ARGS = {
    'ckpt_dir': ckpt_dir,
    'model': model,
    'optimizer': optimizer,
    'scheduler': scheduler,
    'step': 0,
    'model_name': 'model',
    'ignore_load': None
}
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 int, ndim 0, dtype family int, 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
read_json Ran
ran; our contract draft was wrong, not the code
y-zheng18/point_odyssey/utils/file_io.py
pointer only (licence: NOASSERTION) · get_code("21dd9ba5d9e47a8f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

read_mp4 Ran
ran on a synthesized input
aharley/pips2/datasets/exportdataset.py
code served (permissive licence) · get_code("7617204334d1d459")
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 4, 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary MP4 file for testing
def create_test_mp4():
    # Create a temporary file
    temp_fd, temp_path = tempfile.mkstemp(suffix='.mp4')
    os.close(temp_fd)
    
    # Use OpenCV to write a simple video file
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    out = cv2.VideoWriter(temp_path, fourcc, 20.0, (100, 100))
    
    # Write a few frames
    for i in range(5):
        frame = np.zeros((100, 100, 3), dtype=np.uint8)
        frame[:, :] = (i * 50, i * 50, i * 50)
        out.write(frame)
    
    out.release()
    return temp_path

test_mp4_path = create_test_mp4()

ARGS = {
    'fn': test_mp4_path
}
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 4, dtype family int — 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
read_obj_file Ran
ran; our contract draft was wrong, not the code
y-zheng18/point_odyssey/render_animal.py
pointer only (licence: NOASSERTION) · get_code("ba4494dbb46634a4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

read_obj_file Ran
ran; our contract draft was wrong, not the code
y-zheng18/point_odyssey/utils/gen_tracking.py
pointer only (licence: NOASSERTION) · get_code("cf0f39e1349d5322")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

reprojection Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
y-zheng18/point_odyssey/utils/gen_tracking.py
pointer only (licence: NOASSERTION) · get_code("5bdab6524d5a227a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, y-zheng18/point_odyssey (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.

bilinear_sampler Not yet run
unverified (harvested, no recorded run)
aliciachenw/PIPsUS/nets/pipsUS.py
code served (permissive licence) · get_code("1ac8cce613d98769")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 10 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
bilinear_sampler 18 other papers
9 dated earlier, 9 later · 7 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2108.00622 (2021-08)
Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
2108.10552 (2021-08)
E-RAFT: Dense Optical Flow from Event Cameras
and 15 more not named here
coords_grid 1 other paper
1 later
2407.16124 (2024-07)
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
load 1 other paper
1 later
2407.16124 (2024-07)
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos

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

PointOdyssey dataset. We provide point correspondence annotations across long continuous videos. Here we visualize pixel-coordinate trajectories from frame 0 to frame 1600 in a sample video from our dataset.

For agents

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

get_harvested_code_for_paper("2307.15055")
get_code_for_paper("2307.15055")
have("2307.15055")

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

curl https://syntology.ai/api/ran/2307.15055.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.15055.svg)](https://syntology.ai/paper/2307.15055)

Connect an agent — have() is free.