SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09875 · CVPR · 2023

A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

Jun Xu, Zhewei Huang, Shuchang Zhou, Ailin Huang, Xiaotao Hu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 2 have no contract verdict; 1 failure 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/2303.09875.json · badge: /api/ran/2303.09875.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
megvii-research/CVPR2023-DMVFN marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
MVFB Ran
ran on a synthesized input · constructed an object; no result was computed
megvii-research/CVPR2023-DMVFN/model/arch.py
code served (permissive licence) · get_code("2b15709b0e8bffb8")
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, MVFB: 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
import torch.nn as nn

torch.manual_seed(0)

# The MVFB module expects:
# - in_planes: number of input channels (x and flow concatenated)
# - num_feature: number of feature channels used internally

# Looking at the forward method:
# - x: input tensor with in_planes channels
# - flow: optical flow tensor with 2 channels (u, v)
# - scale: scalar factor for interpolation
# So in_planes should be channels_of_x + 2 (for flow)

# Let's use:
# - in_planes: 5 (3 for image + 2 for flow)
# - num_feature: 16 (must be even for num_feature // 2 and num_feature // 4)

in_planes = 5
num_feature = 16

ARGS = {
    "in_planes": in_planes,
    "num_feature": num_feature,
}
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 MVFB — 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 MVFB 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
RoundSTE Ran
ran on a synthesized input · constructed an object; no result was computed
megvii-research/CVPR2023-DMVFN/model/arch.py
code served (permissive licence) · get_code("44216cabdd941590")
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, RoundSTE: 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

torch.manual_seed(0)

# RoundSTE.forward takes ctx and x
# x is used in torch.bernoulli(x), so it should be a tensor with values in [0, 1]
# RoundSTE.backward takes ctx and grad
# grad is returned as-is, so it's a tensor matching the output shape

# Create a small tensor with values in [0, 1] for bernoulli sampling
x = torch.rand(2, 4)

ARGS = {
    'x': x
}
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 RoundSTE — 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 RoundSTE 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
warp Ran
ran; our contract draft was wrong, not the code
megvii-research/CVPR2023-DMVFN/model/arch.py
code served (permissive licence) · get_code("8a3307b80dfb6871")
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 4, dtype family float, shape (2, 3, 3, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 optical flow tensor
# Shape: (batch=2, channels=2, height=3, width=4)
# The 2 channels represent (u, v) flow components
tenFlow = torch.randn(2, 2, 3, 4)

# Create a small input image tensor
# Shape: (batch=2, channels=3, height=3, width=4)
# 3 channels for RGB
tenInput = torch.randn(2, 3, 3, 4)

ARGS = {
    'tenInput': tenInput,
    'tenFlow': tenFlow
}
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 4, dtype family float, shape (2, 3, 3, 4) — shape (2, 3, 3, 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
DMVFN Not yet run
unverified (harvested, no recorded run)
megvii-research/CVPR2023-DMVFN/model/arch.py
code served (permissive licence) · get_code("d521cc2d3ec89658")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra inputs, e.g., semantic/depth maps, for promising performance. For efficiency consideration, in this paper, we propose a Dynamic Multi-scale Voxel Flow Network (DMVFN) to achieve better video prediction performance at lower computational costs with only RGB images, than previous methods. The core of our DMVFN is a differentiable routing module that can effectively perceive the motion scales of video frames. Once trained, our DMVFN selects adaptive sub-networks for different inputs at the inference stage. Experiments on several benchmarks demonstrate that our DMVFN is an order of magnitude faster than Deep Voxel Flow [35] and surpasses the state-of-the-art iterative-based OPT [63] on generated image quality.

For agents

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

get_harvested_code_for_paper("2303.09875")
get_code_for_paper("2303.09875")
have("2303.09875")

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

curl https://syntology.ai/api/ran/2303.09875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09875.svg)](https://syntology.ai/paper/2303.09875)

Connect an agent — have() is free.