SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07449 · ICLR · 2024

PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

Philip Torr, Victor Prisacariu, Jia-Wang Bian, Wenjing Bian

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 0 have no contract verdict; 2 failures of our instrument; 2 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/2310.07449.json · badge: /api/ran/2310.07449.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
ActiveVisionLab/porf canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
pose_alignment Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ActiveVisionLab/porf/export_camera_file.py
code served (permissive licence) · get_code("822da371ec006a2b")
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 ndarray, ndim 3, dtype family float, shape (3, 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

# Create sample pose matrices (4x4 transformation matrices)
# poses_pred: predicted poses, shape (num_poses, 4, 4)
# poses_gt: ground truth poses, shape (num_gt, 4, 4)

num_poses = 3
num_gt = 2

# Create predicted poses
poses_pred = np.zeros((num_poses, 4, 4))
for i in range(num_poses):
    poses_pred[i] = np.eye(4)
    poses_pred[i, :3, 3] = np.array([i + 1.0, i + 2.0, i + 3.0])

# Create ground truth poses
poses_gt = np.zeros((num_gt, 4, 4))
for i in range(num_gt):
    poses_gt[i] = np.eye(4)
    poses_gt[i, :3, 3] = np.array([i + 1.5, i + 2.5, i + 3.5])

ARGS = {
    "poses_pred": poses_pred,
    "poses_gt": poses_gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 3, dtype family float, shape (3, 4, 4) — shape (3, 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
umeyama_alignment Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ActiveVisionLab/porf/export_camera_file.py
code served (permissive licence) · get_code("f333ce486a16e9db")
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 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 numpy as np

# Create small point clouds for alignment
# x and y should be mxn matrices where m is dimension and n is number of points
np.random.seed(0)

# Create two point sets: 3D points (m=3), with 5 data points (n=5)
m, n = 3, 5
x = np.random.randn(m, n).astype(np.float64)
y = np.random.randn(m, n).astype(np.float64)

ARGS = {
    "x": x,
    "y": y,
    "with_scale": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
PoRF Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/porf/models/networks.py
code served (permissive licence) · get_code("3dcf8fd84053ce95")
How it ran

no invocation recorded.

make_c2w Not yet run
unverified (harvested, no recorded run)
ActiveVisionLab/porf/models/networks.py
code served (permissive licence) · get_code("d0a3f789a936f782")
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

Neural surface reconstruction is sensitive to the camera pose noise, even if stateof-the-art pose estimators like COLMAP or ARKit are used. More importantly, existing Pose-NeRF joint optimisation methods have struggled to improve pose accuracy in challenging real-world scenarios. To overcome the challenges, we introduce the pose residual field (PoRF), a novel implicit representation that uses an MLP for regressing pose updates. This is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence. Furthermore, we propose an epipolar geometry loss to enhance the supervision that leverages the correspondences exported from COLMAP results without the extra computational overhead. Our method yields promising results. On the DTU dataset, we reduce the rotation error by 78% for COLMAP poses, leading to the decreased reconstruction Chamfer distance from 3.48mm to 0.85mm. On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69.18 to 75.67, outperforming that with the dataset provided ground-truth pose (75.14). Moreover, we integrate our method into the Nerfstudio library, consistently improving performance in diverse challenging scenes. These achievements demonstrate the efficacy of our approach in refining camera poses in real-world scenarios.

For agents

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

get_harvested_code_for_paper("2310.07449")
get_code_for_paper("2310.07449")
have("2310.07449")

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

curl https://syntology.ai/api/ran/2310.07449.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.07449.svg)](https://syntology.ai/paper/2310.07449)

Connect an agent — have() is free.