SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02416 · CVPR · 2024

ODIN: A Single Model for 2D and 3D Segmentation

Ayush Jain, Katerina Fragkiadaki, Nikolaos Gkanatsios, Vishrav Chaudhary, Adam Harley, Gabriel Sarch, Kriti Aggarwal, Pushkal Katara

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 7 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/2401.02416.json · badge: /api/ran/2401.02416.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
ayushjain1144/odin canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_dice_loss Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/modeling/matcher.py
code served (permissive licence) · get_code("bc2cb481a75c370d")
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 Tensor, ndim 2, dtype family float, shape (2, 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)

# Create small tensors for inputs and targets
# inputs: arbitrary shape float tensor (predictions)
# targets: same shape as inputs, binary classification labels (0 or 1)
# Using shape (2, 4) - batch size 2, 4 features
inputs = torch.randn(2, 4, dtype=torch.float32)
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

ARGS = {
    'inputs': inputs,
    'targets': targets,
}
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 Tensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 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
calculate_uncertainty Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ayushjain1144/odin/odin/modeling/criterion.py
code served (permissive licence) · get_code("2dcb8123d89bb1ff")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 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 torch

torch.manual_seed(0)

# logits should be a tensor of shape (R, 1, ...) where R is number of predictions
# The function expects logits.shape[1] == 1
# Let's create a tensor with shape (2, 1, 4, 3) - R=2, C=1, and spatial dims 4x3
logits = torch.randn(2, 1, 4, 3)

ARGS = {
    "logits": logits
}
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 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
collate_fn Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/data_video/build.py
code served (permissive licence) · get_code("477e6413e38c667b")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np
import copy

torch.manual_seed(0)
np.random.seed(0)

# Construct a batch of sample dicts
# Each sample needs keys that the function checks for
batch = []

for sample_idx in range(2):
    sample = {
        'do_camera_drop': True,  # controls do_view_aug
        'max_frames': 4,  # number of frames
        'use_ghost': False,
        # List of length max_frames (will be subsampled)
        'images': [torch.randn(3, 8) for _ in range(4)],
        # List of length max_frames with instances
        'instances_all': [
            [torch.randn(2, 5), torch.randn(1, 5)],  # frame 0: 2 instances
            [torch.randn(3, 5)],                      # frame 1: 3 instances
            [torch.randn(1, 5)],                      # frame 2: 1 instance
            [torch.randn(2, 5)]                       # frame 3: 2 instances
        ],
        # Tensor of shape (max_frames, ...) that will be indexed
        'poses': torch.randn(4, 7),
        # special_keys example: list of tensors, each with max_frames in dim 0
        'multi_scale_xyz': [
            torch.randn(4, 10),  # first scale
            torch.randn(4, 15),  # second scale
        ],
    }
    batch.append(sample)

# The function modifies batch in-place and returns it
ARGS = {
    'batch': batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
custom_image_augmentations Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/data_video/dataset_mapper_scannet.py
code served (permissive licence) · get_code("a26f0c5d307ec0ab")
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 Compose. 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
from torchvision import transforms as pt_transforms

torch.manual_seed(0)

# The function takes one parameter: is_train (a boolean)
# It returns a transforms.Compose object if is_train is True, else None
# We'll test both cases by creating two separate argument sets

# Test case 1: is_train = True
ARGS = {
    "is_train": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
dice_loss Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/modeling/criterion.py
code served (permissive licence) · get_code("89f75e54ff128be0")
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 Tensor, ndim 0, dtype family float, shape () 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 small tensors for inputs and targets
# inputs should be arbitrary shape that can be flattened
inputs = torch.randn(2, 4, requires_grad=False)  # batch_size=2, features=4
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)  # same shape as inputs, binary labels

# num_masks is a float representing the number of masks for normalization
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
intersection_and_union_gpu Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/data_video/scannet_3d_eval_semantic.py
code served (permissive licence) · get_code("7d7d9cdce5fee3dc")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 small tensors for output and target
# output and target must have the same shape
# The function reshapes them to 1D, so they can be any shape initially
batch_size = 2
height = 3
width = 4

# output: predicted class indices (should be in range [0, k-1])
output = torch.randint(0, 5, (batch_size, height, width))

# target: ground truth class indices (should be in range [0, k-1] or ignore_index)
target = torch.randint(0, 5, (batch_size, height, width))

# k: number of classes
k = 5

# ignore_index: class index to ignore in computation
ignore_index = -1

ARGS = {
    'output': output,
    'target': target,
    'k': k,
    'ignore_index': ignore_index,
}
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
sigmoid_ce_loss Ran
ran; our contract draft was wrong, not the code
ayushjain1144/odin/odin/modeling/criterion.py
code served (permissive licence) · get_code("d0c61e8dba511aa3")
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 Tensor, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs: predictions (logits), arbitrary shape
# targets: binary labels (0 or 1), same shape as inputs
batch_size = 2
num_elements = 4

inputs = torch.randn(batch_size, num_elements, dtype=torch.float32)
targets = torch.randint(0, 2, (batch_size, num_elements), dtype=torch.float32)

# num_masks: used as divisor in the loss computation
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
batch_sigmoid_ce_loss Not yet run
unverified (harvested, no recorded run)
ayushjain1144/odin/odin/modeling/matcher.py
code served (permissive licence) · get_code("1edd24985036b0bf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 5 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
dice_loss 46 other papers
30 dated earlier, 2 the same month, 13 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 43 more not named here
sigmoid_ce_loss 45 other papers
29 dated earlier, 2 the same month, 13 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 42 more not named here
batch_dice_loss 44 other papers
27 dated earlier, 1 the same month, 15 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
batch_sigmoid_ce_loss 44 other papers
27 dated earlier, 1 the same month, 15 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
calculate_uncertainty 34 other papers
21 dated earlier, 1 the same month, 10 later, 2 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.04187 (2022-03)
RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
and 31 more not named here

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

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label datasetprovided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus postprocessed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website https://odin-seg.github.io.

For agents

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

get_harvested_code_for_paper("2401.02416")
get_code_for_paper("2401.02416")
have("2401.02416")

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

curl https://syntology.ai/api/ran/2401.02416.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02416.svg)](https://syntology.ai/paper/2401.02416)

Connect an agent — have() is free.