SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.04400 · ICLR · 2024

LRM: Large Reconstruction Model for Single Image to 3D

Trung Bui, Feng Liu, Hao Tan, Jiuxiang Gu, Yang Zhou, Yicong Hong, Ai Zhang, Sai Bi, Difan Liu, Kalyan Sunkavalli

arXiv · PDF · Open in the Atlas

Code that ran

3 of 11 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; 2 failures of our instrument; 8 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/2311.04400.json · badge: /api/ran/2311.04400.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
3dtopia/openlrm community
Papers with Code archive
3 ran · 8 no recorded run
FunctionStatusWhere it lives
generate_planes Ran
ran on a synthesized input
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("82cca84db633db1e")
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; 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)

ARGS = {}
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 — no output shape is stated: observe_signature.py could not observe it (no_inputs)
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
project_onto_planes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("deea8f5d7aa1ffb1")
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 (6, 4, 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)

# planes: shape (n_planes, 3, 3) - batch of 3x3 transformation matrices
n_planes = 2
planes = torch.randn(n_planes, 3, 3)

# coordinates: shape (N, M, 3) - N batches of M 3D points
N = 3
M = 4
coordinates = torch.randn(N, M, 3)

ARGS = {
    "planes": planes,
    "coordinates": coordinates,
}
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 (6, 4, 2) — shape (6, 4, 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
sample_from_planes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("8ffc27d7787dfbea")
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, 4, 5, 8) 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)

# Examine the function to understand what's needed:
# - plane_axes: passed to project_onto_planes, shape should be (n_planes, 3, 3)
# - plane_features: shape (N, n_planes, C, H, W), used in view and grid_sample
# - coordinates: shape (N, M, 3), passed to project_onto_planes
# - mode: string, default 'bilinear'
# - padding_mode: string, must be 'zeros'
# - box_warp: scalar, used in division operation

N = 2
n_planes = 4
C = 8
H = 16
W = 16
M = 5

# Create plane_axes: (n_planes, 3, 3) - must be invertible
# Use identity-like matrices scaled slightly differently for each plane
plane_axes = torch.zeros(n_planes, 3, 3)
for i in range(n_planes):
    plane_axes[i] = torch.eye(3) * (1.0 + i * 0.1)

# Create plane_features: (N, n_planes, C, H, W)
plane_features = torch.randn(N, n_planes, C, H, W)

# Create coordinates: (N, M, 3)
coordinates = torch.randn(N, M, 3) * 0.5

# mode parameter
mode = 'bilinear'

# padding_mode parameter (must be 'zeros' based on assertion)
padding_mode = 'zeros'

# box_warp parameter - scalar value used for scaling
box_warp = 2.0

ARGS = {
    'plane_axes': plane_axes,
    'plane_features': plane_features,
    'coordinates': coordinates,
    'mode': mode,
    'padding_mode': padding_mode,
    'box_warp': box_warp,
}
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, 4, 5, 8) — shape (2, 4, 5, 8) 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
CameraEmbedder Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("6de65438082ba860")
How it ran

no invocation recorded.

ImportanceRenderer Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("f0c2c618df61c74d")
How it ran

no invocation recorded.

MipRayMarcher2 Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("b6c4459a4a0dbc8e")
How it ran

no invocation recorded.

ModelLRM Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("f0f390e08f896460")
How it ran

no invocation recorded.

OSGDecoder Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("f74da9975ef05b99")
How it ran

no invocation recorded.

RaySampler Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("4dba7d483be44947")
How it ran

no invocation recorded.

TransformerDecoder Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("7fae60cebd3098e3")
How it ran

no invocation recorded.

TriplaneSynthesizer Not yet run
unverified (harvested, no recorded run)
3dtopia/openlrm/openlrm/models/modeling_lrm.py
code served (permissive licence) · get_code("b93b079769f92cca")
How it ran

no invocation recorded.

Also present in other papers' code

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

We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs, including real-world in-the-wild captures and images created by generative models. Video demos and interactable 3D meshes can be found on our LRM project webpage: https://yiconghong.me/LRM. ˚Intern at Adobe Research.

For agents

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

get_harvested_code_for_paper("2311.04400")
get_code_for_paper("2311.04400")
have("2311.04400")

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

curl https://syntology.ai/api/ran/2311.04400.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.04400.svg)](https://syntology.ai/paper/2311.04400)

Connect an agent — have() is free.