SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.04508 · 2023

InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 0 failures of our instrument; 5 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/2303.04508.json · badge: /api/ran/2303.04508.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
ROKIT-Healthcare/FastSurf canonical (classifier label)
classifier basis not recorded on the link
11 ran · 5 no recorded run
FunctionStatusWhere it lives
alphanum_key Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/datasets/load_scannet.py
code served (permissive licence) · get_code("74b478a4068c1cb6")
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 re

def alphanum_key(s):
    """ Turn a string into a list of string and number chunks.
        "z23a" -> ["z", 23, "a"]
    """
    return [int(x) if x.isdigit() else x for x in re.split('([0-9]+)', s)]

ARGS = {
    "s": "z23a"
}
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
create_grid Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/grid.py
code served (permissive licence) · get_code("44e4ce5907854b38")
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 DenseGrid. 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'type': 'DenseGrid',
    'channels': 3,
    'world_size': [4, 5, 6],
    'xyz_min': [0.0, 0.0, 0.0],
    'xyz_max': [1.0, 1.0, 1.0]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DenseGrid — a DenseGrid output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseGrid 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
focal_to_fov Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/eval/frustum_culling.py
code served (permissive licence) · get_code("3f06412d2d75a841")
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 math

def focal_to_fov(focal, height):
    return math.degrees(2.0 * math.atan(height / (2.0 * focal)))

ARGS = {
    "focal": 500.0,
    "height": 480
}
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 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
fov_to_focal Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/eval/frustum_culling.py
code served (permissive licence) · get_code("9ebc9d572e0d19a5")
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 math
import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "fov": 45.0,
    "height": 480
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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
get_batch_query_fn Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/extract_mesh.py
code served (permissive licence) · get_code("07266a2aab8084b1")
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 function. 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 query function that accepts the specified parameters
def dummy_query_fn(features, viewdirs=None, feature_array=None, pose_array=None, 
                   frame_ids=None, per_frame_alignment=None, deformation_field=None, 
                   c2w_array=None, network_fn=None):
    # Simple dummy implementation that returns a tensor
    batch_size = features.shape[0]
    return torch.randn(batch_size, 3)

# Create a simple network function as a small nn.Module
class DummyNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create feature array - shape (2, 4) for batch=2, feature_dim=4
feature_array = torch.randn(2, 4)

# Create network function
network_fn = DummyNetwork()

# Package arguments
ARGS = {
    'query_fn': dummy_query_fn,
    'feature_array': feature_array,
    'network_fn': network_fn
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_embedder_obj Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/nerf_helpers.py
code served (permissive licence) · get_code("251fc8a881780ad8")
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 Embedder. 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)

ARGS = {
    'multires': 4
}
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 Embedder — a Embedder output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Embedder 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_projection_matrix Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/eval/frustum_culling.py
code served (permissive licence) · get_code("2dcbd49142f39412")
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 (4, 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 numpy as np
import math

ARGS = {
    "fov": 45.0,
    "aspect": 1.777,
    "near": 0.1,
    "far": 100.0
}
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 (4, 4) — shape (4, 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
get_scene_bounds Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/scene_bounds.py
code served (permissive licence) · get_code("827f3a1588ea2263")
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

torch.manual_seed(0)

ARGS = {
    "scene_name": "scene0000",
    "voxel_size": 0.1,
    "sc_factor": 1,
    "interp": False,
}
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 — 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
load_first_pose Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/eval/dataloader_util.py
code served (permissive licence) · get_code("22c9a649c43f4fe3")
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 (4, 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 os
import tempfile
import numpy as np

# Create a temporary directory with a pose file
tmpdir = tempfile.mkdtemp()
pose_file = "poses.txt"
pose_path = os.path.join(tmpdir, pose_file)

# Write 4 lines of pose data (floats separated by spaces)
with open(pose_path, 'w') as f:
    f.write("1.0 2.0 3.0 4.0\n")
    f.write("5.0 6.0 7.0 8.0\n")
    f.write("9.0 10.0 11.0 12.0\n")
    f.write("13.0 14.0 15.0 16.0\n")

ARGS = {
    "datadir": tmpdir,
    "pose_file": pose_file
}
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 (4, 4) — shape (4, 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
load_focal_length Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/datasets/load_scannet.py
code served (permissive licence) · get_code("b34e7e28f93c1583")
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 tempfile
import os

# Create a temporary file with a focal length value
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write('50.5')
temp_file.close()
temp_filepath = temp_file.name

try:
    ARGS = {
        'filepath': temp_filepath
    }
finally:
    # Clean up will happen after ARGS is defined
    pass
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 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
load_poses Ran
ran on a synthesized input
ROKIT-Healthcare/FastSurf/datasets/load_scannet.py
code served (permissive licence) · get_code("c30c27242d09e709")
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 tempfile
import os

# Create a temporary pose file with valid and invalid poses
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("1.0 0.0 0.0 0.0\n")
temp_file.write("0.0 1.0 0.0 0.0\n")
temp_file.write("0.0 0.0 1.0 0.0\n")
temp_file.write("0.0 0.0 0.0 1.0\n")
temp_file.write("nan 0.0 0.0 0.0\n")
temp_file.write("0.0 1.0 0.0 0.0\n")
temp_file.write("0.0 0.0 1.0 0.0\n")
temp_file.write("0.0 0.0 0.0 1.0\n")
temp_file.close()

ARGS = {
    'posefile': temp_file.name
}
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 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
cull_by_bounds Not yet run
unverified (harvested, no recorded run)
ROKIT-Healthcare/FastSurf/eval/cull_mesh.py
code served (permissive licence) · get_code("8b1e8b9af1a7debb")
How it ran

no invocation recorded.

get_masks Not yet run
unverified (harvested, no recorded run)
ROKIT-Healthcare/FastSurf/losses.py
code served (permissive licence) · get_code("865d49d44a21dc85")
How it ran

no invocation recorded.

get_scene_bound Not yet run
unverified (harvested, no recorded run)
ROKIT-Healthcare/FastSurf/optimize.py
code served (permissive licence) · get_code("c807eff4153ef3b9")
How it ran

no invocation recorded.

get_view_frustum Not yet run
unverified (harvested, no recorded run)
ROKIT-Healthcare/FastSurf/optimize.py
code served (permissive licence) · get_code("6c739c53b8ec2bdc")
How it ran

no invocation recorded.

rigid_transform Not yet run
unverified (harvested, no recorded run)
ROKIT-Healthcare/FastSurf/optimize.py
code served (permissive licence) · get_code("11f8b23014d15eb0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
rigid_transform 9 other papers
5 dated earlier, 3 later, 1 same year, order not determinable
2111.06389 (2021-11)
Full-Body Visual Self-Modeling of Robot Morphologies
2112.00236 (2021-12)
VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion
2204.01139 (2022-04)
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion
and 6 more not named here

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 introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous methods that have employed feature encoding to improve optimization speed, we further improve the reconstruction quality with minimal impact on optimization time by refining depth information. InFusionSurf addresses camera motion-induced blurs in each depth frame through a per-frame intrinsic refinement scheme. It incorporates the truncated signed distance field (TSDF) Fusion, a classical real-time 3D surface reconstruction method, as a pretraining tool for the feature grid, enhancing reconstruction details and training speed. Comparative quantitative and qualitative analyses show that InFusionSurf reconstructs scenes with high accuracy while maintaining optimization efficiency. The effectiveness of our intrinsic refinement and TSDF Fusion-based pretraining is further validated through an ablation study.

For agents

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

get_harvested_code_for_paper("2303.04508")
get_code_for_paper("2303.04508")
have("2303.04508")

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

curl https://syntology.ai/api/ran/2303.04508.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.04508.svg)](https://syntology.ai/paper/2303.04508)

Connect an agent — have() is free.