SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.16397 · CVPR · 2021

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding

Chaozheng Wu, Kui Jia, Ke Chen, Xun Xu, Shengheng Deng

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 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/2103.16397.json · badge: /api/ran/2103.16397.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
Gorilla-Lab-SCUT/AffordanceNet canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
build_dataset Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/AffordanceNet/utils/builder.py
code served (permissive licence) · get_code("4ee4a7435a0d609e")
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
import torch.nn as nn
from unittest.mock import Mock, MagicMock

torch.manual_seed(0)

# Create stand-in dataset classes that match the function's expectations
class AffordNetDataset:
    def __init__(self, data_root, split, partial=False, rotate='None', semi=False):
        self.data_root = data_root
        self.split = split
        self.partial = partial
        self.rotate = rotate
        self.semi = semi

class AffordNetDataset_Unlabel:
    def __init__(self, data_root):
        self.data_root = data_root

# Create a config object with the required structure
class DataConfig:
    def __init__(self):
        self.data_root = '/tmp/data'
        self.category = 'affordance'

class TrainingConfig:
    def __init__(self):
        self._config = {
            'partial': False,
            'rotate': 'None',
            'semi': False
        }
    
    def get(self, key, default=None):
        return self._config.get(key, default)

class Config:
    def __init__(self):
        self.data = DataConfig()
        self.training_cfg = TrainingConfig()

# Inject the dataset classes into the module scope so build_dataset can access them
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'AffordNetDataset', AffordNetDataset)
setattr(current_module, 'AffordNetDataset_Unlabel', AffordNetDataset_Unlabel)

# Create instances for the arguments
cfg = Config()

ARGS = {
    'cfg': cfg,
    'test': 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 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
build_loader Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/AffordanceNet/utils/builder.py
code served (permissive licence) · get_code("16179f76ca18ce19")
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
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader

torch.manual_seed(0)

# Create a minimal Dataset class
class DummyDataset(Dataset):
    def __init__(self, size=4):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        x = torch.randn(3)
        y = torch.tensor(idx % 2)
        return x, y

# Create a config class with the necessary attributes
class TrainingConfig:
    def __init__(self):
        self.batch_size = 8
        self._semi = False
    
    def get(self, key, default=False):
        if key == 'semi':
            return self._semi
        return default

class Config:
    def __init__(self):
        self.training_cfg = TrainingConfig()

# Create datasets
train_set = DummyDataset(size=8)
val_set = DummyDataset(size=4)
train_unlabel_set = DummyDataset(size=6)

# Create dataset_dict with train/val sets
dataset_dict = {
    'train_set': train_set,
    'val_set': val_set,
    'train_unlabel_set': train_unlabel_set
}

# Create config
cfg = Config()

ARGS = {
    'cfg': cfg,
    'dataset_dict': dataset_dict
}
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
knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Gorilla-Lab-SCUT/AffordanceNet/models/dgcnn.py
code served (permissive licence) · get_code("cdd0141594039dcb")
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 Tensor, ndim 3, dtype family int, shape (2, 3, 2) 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

torch.manual_seed(0)

# x is used with:
# - transpose(2, 1): expects 3D tensor
# - matmul with transposed version: matrix multiplication
# - sum(x ** 2, dim=1, keepdim=True): sum over dimension 1
# - topk(k=k, dim=-1): get top k indices along last dimension
# 
# Shape should be (batch, features, num_points) based on the transpose operations
# Let's use batch=2, features=4, num_points=3

x = torch.randn(2, 4, 3)

# k is the number of nearest neighbors to find
# Should be less than num_points (3), so k=2
k = 2

ARGS = {
    "x": x,
    "k": k,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 3, dtype family int, shape (2, 3, 2) — shape (2, 3, 2) 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
normalize_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Gorilla-Lab-SCUT/AffordanceNet/utils/provider.py
pointer only (licence: MIT); the stored copy get_code serves, from Levishery/Flywire-Neuron-Tracing, is pointer only (licence: NONE) · get_code("59e9008f0a3743f1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Levishery/Flywire-Neuron-Tracing, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pc_normalize Ran
ran, honoured the contract we drafted
Gorilla-Lab-SCUT/AffordanceNet/models/pointnet_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aboulch/ConvPoint, is pointer only (licence: NOASSERTION) · get_code("ec413739d406e611")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aboulch/ConvPoint, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pc_normalize Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/AffordanceNet/dataset/AffordanceNet.py
code served (permissive licence) · get_code("a35d3df543c7cc58")
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 numpy as np

# pc_normalize takes a point cloud array and normalizes it
# pc parameter: numpy array of shape (N, 3) or (N, D) representing N points in D dimensions

# Create a small point cloud with 5 points in 3D space
pc = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0],
    [2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0]
], dtype=np.float32)

ARGS = {
    'pc': pc
}
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
semi_points_transform Ran
ran, honoured the contract we drafted
Gorilla-Lab-SCUT/AffordanceNet/dataset/AffordanceNet.py
code served (permissive licence) · get_code("109780e2940e1431")
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 (2, 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 a small point cloud with shape (2, 4)
# 2 points, 4 dimensions
points = np.array([
    [0.0, 1.0, 2.0, 3.0],
    [0.5, 1.5, 2.5, 3.5]
], dtype=np.float32)

ARGS = {
    "points": points
}
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 (2, 4) — shape (2, 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
shuffle_data Ran
ran; our contract draft was wrong, not the code
Gorilla-Lab-SCUT/AffordanceNet/utils/provider.py
pointer only (licence: MIT); the stored copy get_code serves, from Levishery/Flywire-Neuron-Tracing, is pointer only (licence: NONE) · get_code("06353aadebc1724b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Levishery/Flywire-Neuron-Tracing, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

shuffle_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Gorilla-Lab-SCUT/AffordanceNet/utils/provider.py
code served (permissive licence) · get_code("a97f76b9c0811c93")
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 3, dtype family float, shape (2, 4, 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 numpy as np

# Create a small batch of point cloud data
# BxNxC format: B=batch size, N=number of points, C=channels (coordinates)
batch_size = 2
num_points = 4
channels = 3

batch_data = np.random.randn(batch_size, num_points, channels).astype(np.float32)

ARGS = {
    "batch_data": batch_data
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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: none by the harness; any seed is in the setup block
square_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Gorilla-Lab-SCUT/AffordanceNet/models/pointnet_util.py
code served (permissive licence) · get_code("580dee6761649b29")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 5) 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

torch.manual_seed(0)

# Create source points: [B, N, C]
# B=2 (batch), N=4 (num source points), C=3 (coordinates)
src = torch.randn(2, 4, 3)

# Create destination points: [B, M, C]
# B=2 (batch), M=5 (num destination points), C=3 (coordinates)
dst = torch.randn(2, 5, 3)

ARGS = {
    "src": src,
    "dst": dst,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 3, dtype family float, shape (2, 4, 5) — shape (2, 4, 5) 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
timeit Ran
ran, honoured the contract we drafted
Gorilla-Lab-SCUT/AffordanceNet/models/pointnet_util.py
pointer only (licence: MIT); the stored copy get_code serves, from duasoi/Mind2Cloud, is pointer only (licence: NONE) · get_code("b1227ddb721e2999")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from duasoi/Mind2Cloud, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_graph_feature Not yet run
unverified (harvested, no recorded run)
Gorilla-Lab-SCUT/AffordanceNet/models/dgcnn.py
code served (permissive licence) · get_code("9019aa1bd21a7d63")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 4 the same month, 9 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.

FunctionAlso present inEarliest-datedOthers named
square_distance 75 other papers
5 dated earlier, 1 the same month, 69 later · 9 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00410 (2020-03)
PF-Net: Point Fractal Network for 3D Point Cloud Completion
and 72 more not named here
knn 52 other papers
7 dated earlier, 1 the same month, 44 later · 12 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
2005.06734 (2020-05)
Dense-Resolution Network for Point Cloud Classification and Segmentation
and 49 more not named here
pc_normalize 36 other papers
7 dated earlier, 1 the same month, 28 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1904.02375 (2019-04)
ConvPoint: Continuous Convolutions for Point Cloud Processing
1904.10014 (2019-04)
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
and 33 more not named here
timeit 33 other papers
3 dated earlier, 30 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00410 (2020-03)
PF-Net: Point Fractal Network for 3D Point Cloud Completion
2003.04618 (2020-03)
Convolutional Occupancy Networks
and 30 more not named here
shuffle_data 17 other papers
9 dated earlier, 8 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1803.11527 (2018-03)
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
and 14 more not named here
get_graph_feature 11 other papers
2 dated earlier, 9 later · 4 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
2101.07296 (2021-01)
Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias
2108.11305 (2021-08)
CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
and 8 more not named here
shuffle_points 11 other papers
3 dated earlier, 1 the same month, 7 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1812.11647 (2018-12)
Path-Invariant Map Networks
2006.14865 (2020-06)
RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud
and 8 more not named here
normalize_data 6 other papers
1 dated earlier, 5 later
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2109.09521 (2021-09)
RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
2303.02401 (2023-03)
Open-Vocabulary Affordance Detection in 3D Point Clouds
and 3 more not named here
pc_normalize 1 other paper
1 later
2303.02401 (2023-03)
Open-Vocabulary Affordance Detection in 3D Point Clouds

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

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant studies in 2D and 2.5D image domains have been made previously, however, a truly functional understanding of object affordance requires learning and prediction in the 3D physical domain, which is still absent in the community. In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visual affordance categories. Based on this dataset, we provide three benchmarking tasks for evaluating visual affordance understanding, including full-shape, partial-view and rotation-invariant affordance estimations. Three state-of-the-art point cloud deep learning networks are evaluated on all tasks. In addition we also investigate a semi-supervised learning setup to explore the possibility to benefit from unlabeled data. Comprehensive results on our contributed dataset show the promise of visual affordance understanding as a valuable yet challenging benchmark.

For agents

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

get_harvested_code_for_paper("2103.16397")
get_code_for_paper("2103.16397")
have("2103.16397")

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

curl https://syntology.ai/api/ran/2103.16397.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.16397.svg)](https://syntology.ai/paper/2103.16397)

Connect an agent — have() is free.