SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03089 · CVPR · 2022

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

Cewu Lu, Yang You, Ruoxi Shi, Weiming Wang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2203.03089.json · badge: /api/ran/2203.03089.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
qq456cvb/CPPF community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
ResLayer Ran
ran on a synthesized input
qq456cvb/CPPF/models/model.py
code served (permissive licence) · get_code("c55ac229030b42bb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 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
import torch.nn.functional as F

class ResLayer(torch.nn.Module):

    def __init__(self, dim_in, dim_out, bn=False) -> None:
        super().__init__()
        assert bn is False
        self.fc1 = torch.nn.Linear(dim_in, dim_out)
        if bn:
            self.bn1 = torch.nn.BatchNorm1d(dim_out)
        else:
            self.bn1 = lambda x: x
        self.fc2 = torch.nn.Linear(dim_out, dim_out)
        if bn:
            self.bn2 = torch.nn.BatchNorm1d(dim_out)
        else:
            self.bn2 = lambda x: x
        if dim_in != dim_out:
            self.fc0 = torch.nn.Linear(dim_in, dim_out)
        else:
            self.fc0 = None

    def forward(self, x):
        x_res = x if self.fc0 is None else self.fc0(x)
        x = F.relu(self.bn1(self.fc1(x)))
        x = self.bn2(self.fc2(x))
        return x + x_res


INIT_ARGS = {
    'dim_in': 4,
    'dim_out': 3,
    'bn': False,
}

ARGS = {
    'x': torch.randn(2, 4),
}

if __name__ == '__main__':
    model = ResLayer(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 3)")
    assert output.shape == (2, 3), f"Shape mismatch: got {output.shape}, expected (2, 3)"
    print("Test passed!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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, 3) — shape (2, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
PPFEncoder Not yet run
unverified (harvested, no recorded run)
qq456cvb/CPPF/models/model.py
code served (permissive licence) · get_code("dc024511f84cf7a6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we tackle the problem of category-level 9D pose estimation in the wild, given a single RGB-D frame. Using supervised data of real-world 9D poses is tedious and erroneous, and also fails to generalize to unseen scenarios. Besides, category-level pose estimation requires a method to be able to generalize to unseen objects at test time, which is also challenging. Drawing inspirations from traditional point pair features (PPFs), in this paper, we design a novel Category-level PPF (CPPF) voting method to achieve accurate, robust and generalizable 9D pose estimation in the wild. To obtain robust pose estimation, we sample numerous point pairs on an object, and for each pair our model predicts necessary SE(3)-invariant voting statistics on object centers, orientations and scales. A novel coarse-to-fine voting algorithm is proposed to eliminate noisy point pair samples and generate final predictions from the population. To get rid of false positives in the orientation voting process, an auxiliary binary disambiguating classification task is introduced for each sampled point pair. In order to detect objects in the wild, we carefully design our sim-to-real pipeline by training on synthetic point clouds only, unless objects have ambiguous poses in geometry. Under this circumstance, color information is leveraged to disambiguate these poses. Results on standard benchmarks show that our method is on par with current state of the arts with realworld training data. Extensive experiments further show that our method is robust to noise and gives promising results under extremely challenging scenarios. Our code is available on https://github.com/qq456cvb/CPPF.

For agents

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

get_harvested_code_for_paper("2203.03089")
get_code_for_paper("2203.03089")
have("2203.03089")

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

curl https://syntology.ai/api/ran/2203.03089.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03089.svg)](https://syntology.ai/paper/2203.03089)

Connect an agent — have() is free.