SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 136750141 · ECCV · 2022

Deep Bayesian Video Frame Interpolation

Yu Zhang, Jimmy Ren, Dongqing Zou, Zhiyang Yu, Xujie Xiang, Xijun Chen

Code that ran

8 of 11 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 7 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/136750141.json · badge: /api/ran/136750141.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
Oceanlib/DBVI canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
backWarp Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/warp.py
code served (permissive licence) · get_code("2c28bc14db97c7fc")
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 5, 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.functional as F

torch.manual_seed(0)

# Create a small image tensor: (batch=2, channels=3, height=4, width=5)
img = torch.randn(2, 3, 4, 5, dtype=torch.float32)

# Create a flow tensor: (batch=2, 2 channels for u and v, height=4, width=5)
flow = torch.randn(2, 2, 4, 5, dtype=torch.float32) * 0.5

ARGS = {
    "img": img,
    "flow": flow,
}
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 5, 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
compute_same_pad Ran
ran, honoured the contract we drafted
Oceanlib/DBVI/DBVI_2x/lib/dlTool.py
pointer only (licence: MIT); the stored copy get_code serves, from y0ast/Glow-PyTorch, is pointer only (licence: NOASSERTION) · get_code("1493e9433f206e03")
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 y0ast/Glow-PyTorch, and GitHub could not classify the licence of that repository (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.

getAllFiles Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/fileTool.py
code served (permissive licence) · get_code("0a8510249e07b7d6")
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
from pathlib import Path

# Create a temporary directory with some test files
with tempfile.TemporaryDirectory() as tmpdir:
    # Create some test files with different extensions
    test_dir = Path(tmpdir)
    
    # Create nested directories and files
    (test_dir / "subdir1").mkdir()
    (test_dir / "subdir1" / "subdir2").mkdir()
    
    (test_dir / "file1.txt").touch()
    (test_dir / "file2.py").touch()
    (test_dir / "subdir1" / "file3.txt").touch()
    (test_dir / "subdir1" / "file4.py").touch()
    (test_dir / "subdir1" / "subdir2" / "file5.txt").touch()
    
    # Now define ARGS with the temporary directory root
    ARGS = {
        "root": str(test_dir),
        "ext": None
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
getScheduler Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/dlTool.py
code served (permissive licence) · get_code("c6d0a9010c26f04a")
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 MultiStepLR. 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 minimal model
model = nn.Linear(4, 3)

# Create an optimizer (required for lr_scheduler.MultiStepLR)
optimizer = Adam(model.parameters(), lr=0.1)

# Define ARGS dictionary with all parameters
ARGS = {
    'optimizer': optimizer,
    'epoch': -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 MultiStepLR — a MultiStepLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiStepLR 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
makeGrid Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/visualTool.py
code served (permissive licence) · get_code("21fc27a1fd73bd47")
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 3, dtype family float, shape (8, 5, 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)

# Create a small batch of images
# Shape: (batch, channels, height, width) = (2, 3, 4, 5)
batchImg = torch.randn(2, 3, 4, 5)

ARGS = {
    "batchImg": batchImg,
    "shape": (2, 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 ndarray, ndim 3, dtype family float, shape (8, 5, 3) — shape (8, 5, 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
mkPath Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/fileTool.py
code served (permissive licence) · get_code("548093699ac7fb6f")
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 bool, 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 tempfile
from pathlib import Path

# Create a temporary directory to use as a base for path creation
temp_base = tempfile.mkdtemp()

# Define a path that doesn't exist yet (so mkdir will succeed)
test_path = Path(temp_base) / "new_directory" / "nested" / "path"

ARGS = {
    "path": str(test_path)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
normalize_tensor Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/model/block.py
code served (permissive licence) · get_code("7be84ddbb3f15aa8")
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 (2, 4) 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 a small tensor with batch size 2 and feature dimension 4
in_feat = torch.randn(2, 4)

ARGS = {
    "in_feat": in_feat
}
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 (2, 4) — shape (2, 4) 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
reduceTensorSum Ran
ran on a synthesized input
Oceanlib/DBVI/DBVI_2x/lib/distTool.py
code served (permissive licence) · get_code("48fb51b5e4bc5462")
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 (2, 4) 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.distributed as dist

torch.manual_seed(0)

# For dist.all_reduce to work in a non-distributed setting, we need to initialize the process group
# In a single-process CPU environment, we use the 'gloo' backend
try:
    if not dist.is_available() or not dist.is_initialized():
        dist.init_process_group(backend='gloo', init_method='tcp://127.0.0.1:29500', rank=0, world_size=1)
except Exception:
    pass

# Create a small tensor (batch=2, dim=4)
tensor = torch.randn(2, 4)

ARGS = {
    'tensor': tensor
}
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 (2, 4) — shape (2, 4) 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
cupy_kernel Not yet run
unverified (harvested, no recorded run)
Oceanlib/DBVI/DBVI_2x/lib/softsplat.py
pointer only (licence: MIT); the stored copy get_code serves, from sichun233746/MoTIF, is pointer only (licence: NONE) · get_code("4ceac51c7b8e4270")
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 sichun233746/MoTIF, 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. No invocation recorded.

getSubDirs Not yet run
unverified (harvested, no recorded run)
Oceanlib/DBVI/DBVI_2x/lib/fileTool.py
code served (permissive licence) · get_code("92342d7c3f06f0db")
How it ran

no invocation recorded.

reduceTensorMean Not yet run
unverified (harvested, no recorded run)
Oceanlib/DBVI/DBVI_2x/lib/distTool.py
code served (permissive licence) · get_code("7bf618b5a5cd140b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 1 later) and 6 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
cupy_kernel 4 other papers
2 later, 2 same year, order not determinable
Danier_ST-MFNet_A_Spatio-Temporal_Multi-Flow_Network_for_Frame_Interpolation_CVPR_2022_paper (2022 (year only))
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
2206.12614 (2022-06)
BokehMe: When Neural Rendering Meets Classical Rendering
2307.03190 (2023-07)
Text-Guided Synthesis of Eulerian Cinemagraphs
and 1 more not named here
compute_same_pad 2 other papers
2 dated earlier · 1 only as an assembly brick
1807.03039 (2018-07)
Glow: Generative Flow with Invertible 1x1 Convolutions
2002.11896 (2020-02)
Gradient Boosted Normalizing Flows
getAllFiles 1 other paper
1 dated earlier
Yu_Training_Weakly_Supervised_Video_Frame_Interpolation_With_Events_ICCV_2021_paper (2021 (year only))
Training Weakly Supervised Video Frame Interpolation with Events
getSubDirs 1 other paper
1 dated earlier
Yu_Training_Weakly_Supervised_Video_Frame_Interpolation_With_Events_ICCV_2021_paper (2021 (year only))
Training Weakly Supervised Video Frame Interpolation with Events
mkPath 1 other paper
1 dated earlier
Yu_Training_Weakly_Supervised_Video_Frame_Interpolation_With_Events_ICCV_2021_paper (2021 (year only))
Training Weakly Supervised Video Frame Interpolation with Events

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 present deep Bayesian video frame interpolation, a novel approach for upsampling a low frame-rate video temporally to its higher frame-rate counterpart. Our approach learns posterior distributions of optical flows and frames to be interpolated, which is optimized via learned gradient descent for fast convergence. Each learned step is a lightweight network manipulating gradients of the log-likelihood of estimated frames and flows. Such gradients, parameterized either explicitly or implicitly, model the fidelity of current estimations when matching real image and flow distributions to explain the input observations. With this approach we show new records on 8 of 10 benchmarks, using an architecture with half the parameters of the state-of-the-art model. Code and models are publicly available at https://github.com/Oceanlib/DBVI.

For agents

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

get_harvested_code_for_paper("136750141")
get_code_for_paper("136750141")
have("136750141")

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

curl https://syntology.ai/api/ran/136750141.json

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

[![Syntology run record](https://syntology.ai/api/ran/136750141.svg)](https://syntology.ai/paper/136750141)

Connect an agent — have() is free.