SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13647 · CVPR · 2024

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

Junjie Chen, Li Niu, Yuming Fang, Jiebin Yan

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 failure 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/2403.13647.json · badge: /api/ran/2403.13647.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
chenbys/MetaPoint canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
obtain_inference_result Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenbys/MetaPoint/mpformer/cmodules/out_func.py
code served (permissive licence) · get_code("e92642b9667147cd")
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 dict. 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)

# Construct arguments for obtain_inference_result

# meta_to_kp: list of metadata-to-keypoint mappings, one per batch element
# The function iterates over it with enumerate, so it just needs to be iterable
meta_to_kp = [None, None]  # batch size 2, content not accessed

# gt_covisibles_s: tensor of shape (batch, num_keypoints, ...)
# Accessed as gt_covisibles_s[b, :, 0].bool()
# So it needs at least 3 dimensions, with dimension 2 having size >= 1
gt_covisibles_s = torch.randint(0, 2, (2, 4, 1)).float()  # batch=2, num_kp=4, channels=1

# ref_point_q: tensor or list of tensors indexed as ref_point_q[b][l]
# Each element is indexed with [visible_s] where visible_s is a boolean mask
# So each element should be a tensor
ref_point_q = [
    [torch.randn(4), torch.randn(4)],  # batch element 0: 2 refinement levels, 4 values each
    [torch.randn(4), torch.randn(4)]   # batch element 1: 2 refinement levels, 4 values each
]

# invisible_score: scalar float (default 0.5)
invisible_score = 0.5

ARGS = {
    'meta_to_kp': meta_to_kp,
    'gt_covisibles_s': gt_covisibles_s,
    'ref_point_q': ref_point_q,
    'invisible_score': invisible_score
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_meta_loss_nbipart Not yet run
unverified (harvested, no recorded run)
chenbys/MetaPoint/mpformer/cmodules/loss_func.py
code served (permissive licence) · get_code("8e9feb7a4c81a02b")
How it ran

no invocation recorded.

get_ref_loss Not yet run
unverified (harvested, no recorded run)
chenbys/MetaPoint/mpformer/cmodules/loss_func.py
code served (permissive licence) · get_code("f57bc5eb6473e3f2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE. Considering that human can quickly perceive potential keypoints of arbitrary objects, we propose a novel framework for CAPE based on such potential keypoints (named as metapoints). Specifically, we maintain learnable embeddings to capture inherent information of various keypoints, which interact with image feature maps to produce meta-points without any support. The produced meta-points could serve as meaningful potential keypoints for CAPE. Due to the inevitable gap between inherency and annotation, we finally utilize the identities and details offered by support keypoints to assign and refine meta-points to desired keypoints in query image. In addition, we propose a progressive deformable point decoder and a slacked regression loss for better prediction and supervision. Our novel framework not only reveals the inherency of keypoints but also outperforms existing methods of CAPE. Comprehensive experiments and in-depth studies on large-scale MP-100 dataset demonstrate the effectiveness of our framework. Code is avaiable at https://github.com/chenbys/MetaPoint

For agents

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

get_harvested_code_for_paper("2403.13647")
get_code_for_paper("2403.13647")
have("2403.13647")

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

curl https://syntology.ai/api/ran/2403.13647.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.13647.svg)](https://syntology.ai/paper/2403.13647)

Connect an agent — have() is free.