SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.15210 · CVPR · 2022

The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution

Yang Cong, Ronghan Chen

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 (1 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 2026-11-22; 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/2205.15210.json · badge: /api/ran/2205.15210.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
GostInShell/PaRI-Conv marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
PaRIConv Ran
ran on a synthesized input · constructed an object; no result was computed
GostInShell/PaRI-Conv/Networks/model.py
code served (permissive licence) · get_code("0aea093de17b042d")
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, PaRIConv: 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)

# Define the feat_select function
def feat_select(feat, ind):
    assert feat.dim() == 3 and ind.dim() == 1
    B, C, N = feat.size()
    BNK = ind.size(0)
    K = int(BNK / (B * N))
    base = torch.arange(B, device=feat.device).view(B, 1, 1).repeat(1, 1, N * K) * N
    return torch.gather(feat, 2, (ind.view(B, 1, N * K) - base).repeat(1, C, 1)).view(B, C, N, K)

# Define the PaRIConv class
class PaRIConv(nn.Module):

    def __init__(self, in_dim, out_dim, feat_dim=8, k=20):
        super(PaRIConv, self).__init__()
        self.k = k
        self.basis_matrix = nn.Conv1d(in_dim, in_dim, kernel_size=1, bias=False)
        self.dynamic_kernel = nn.Sequential(nn.Conv2d(feat_dim, in_dim // 2, kernel_size=1), nn.BatchNorm2d(in_dim // 2), nn.ReLU(), nn.Conv2d(in_dim // 2, in_dim, kernel_size=1))
        self.act = nn.Sequential(nn.BatchNorm2d(in_dim), nn.ReLU())
        self.edge_conv = nn.Sequential(nn.Conv2d(in_dim * 2, out_dim, kernel_size=1, bias=False), nn.BatchNorm2d(out_dim), nn.LeakyReLU(negative_slope=0.2))

    def forward(self, x, APPF, edge_index, bs):
        _, C = APPF.size()
        APPF = APPF.view(bs, -1, self.k, C).permute(0, 3, 1, 2).contiguous()
        row, col = edge_index
        feat = self.act(self.dynamic_kernel(APPF) * feat_select(self.basis_matrix(x), col))
        pad_x = x.unsqueeze(-1).repeat(1, 1, 1, self.k)
        return self.edge_conv(torch.cat((feat - pad_x, pad_x), dim=1)).max(dim=-1, keepdim=False)[0]

# Build arguments for PaRIConv
in_dim = 8
out_dim = 16
feat_dim = 8
k = 20

ARGS = {
    'in_dim': in_dim,
    'out_dim': out_dim,
    'feat_dim': feat_dim,
    'k': k
}
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 PaRIConv — 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 PaRIConv 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
feat_select Not yet run
unverified (harvested, no recorded run)
GostInShell/PaRI-Conv/Networks/model.py
code served (permissive licence) · get_code("b956f752e03f28fb")
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 2026-11-22.

Repositories linked to this paper

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

Abstract

Recent progress in introducing rotation invariance (RI) to 3D deep learning methods is mainly made by designing RI features to replace 3D coordinates as input. The key to this strategy lies in how to restore the global information that is lost by the input RI features. Most state-of-thearts achieve this by incurring additional blocks or complex global representations, which is time-consuming and ineffective. In this paper, we real that the global information loss stems from an unexplored pose information loss problem, i.e., common convolution layers cannot capture the relative poses between RI features, thus hindering the global information to be hierarchically aggregated in the deep networks. To address this problem, we develop a Pose-aware Rotation Invariant Convolution (i.e., PaRI-Conv), which dynamically adapts its kernels based on the relative poses. Specifically, in each PaRI-Conv layer, a lightweight Augmented Point Pair Feature (APPF) is designed to fully encode the RI relative pose information. Then, we propose to synthesize a factorized dynamic kernel, which reduces the computational cost and memory burden by decomposing it into a shared basis matrix and a pose-aware diagonal matrix that can be learned from the APPF. Extensive experiments on shape classification and part segmentation tasks show that our PaRI-Conv surpasses the state-of-the-art RI methods while being more compact and efficient.

For agents

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

get_harvested_code_for_paper("2205.15210")
get_code_for_paper("2205.15210")
have("2205.15210")

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

curl https://syntology.ai/api/ran/2205.15210.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.15210.svg)](https://syntology.ai/paper/2205.15210)

Connect an agent — have() is free.