SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.13090 · CVPR · 2021

IBRNet: Learning Multi-View Image-Based Rendering

Noah Snavely, Jonathan Barron, Thomas Funkhouser, Kyle Genova, Qianqian Wang, Ricardo Martin-Brualla, Pratul Srinivasan, Howard Zhou, Zhicheng Wang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure 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/2102.13090.json · badge: /api/ran/2102.13090.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
googleinterns/ibrnet community
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
IBRNet Ran
ran on a synthesized input · constructed an object; no result was computed
googleinterns/ibrnet/ibrnet/mlp_network.py
code served (permissive licence) · get_code("b2deeaf748dd7b50")
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, IBRNet: 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
import numpy as np

torch.manual_seed(0)

class MockArgs:
    def __init__(self):
        self.anti_alias_pooling = False
        self.local_rank = 0

ARGS = {
    'args': MockArgs(),
    'in_feat_ch': 32,
    'n_samples': 64,
}
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 IBRNet — 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 IBRNet 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
MultiHeadAttention Ran
ran on a synthesized input
googleinterns/ibrnet/ibrnet/mlp_network.py
code served (permissive licence) · get_code("e415eac8d6b1e84c")
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 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 torch
import torch.nn as nn
import torch.nn.functional as F

class ScaledDotProductAttention(nn.Module):
    """ Scaled Dot-Product Attention """

    def __init__(self, temperature, attn_dropout=0.1):
        super().__init__()
        self.temperature = temperature

    def forward(self, q, k, v, mask=None):
        attn = torch.matmul(q / self.temperature, k.transpose(2, 3))
        if mask is not None:
            attn = attn.masked_fill(mask == 0, -1000000000.0)
        attn = F.softmax(attn, dim=-1)
        output = torch.matmul(attn, v)
        return (output, attn)

class MultiHeadAttention(nn.Module):
    """ Multi-Head Attention module """

    def __init__(self, n_head, d_model, d_k, d_v, dropout=0.1):
        super().__init__()
        self.n_head = n_head
        self.d_k = d_k
        self.d_v = d_v
        self.w_qs = nn.Linear(d_model, n_head * d_k, bias=False)
        self.w_ks = nn.Linear(d_model, n_head * d_k, bias=False)
        self.w_vs = nn.Linear(d_model, n_head * d_v, bias=False)
        self.fc = nn.Linear(n_head * d_v, d_model, bias=False)
        self.attention = ScaledDotProductAttention(temperature=d_k ** 0.5)
        self.layer_norm = nn.LayerNorm(d_model, eps=1e-06)

    def forward(self, q, k, v, mask=None):
        d_k, d_v, n_head = (self.d_k, self.d_v, self.n_head)
        sz_b, len_q, len_k, len_v = (q.size(0), q.size(1), k.size(1), v.size(1))
        residual = q
        q = self.w_qs(q).view(sz_b, len_q, n_head, d_k)
        k = self.w_ks(k).view(sz_b, len_k, n_head, d_k)
        v = self.w_vs(v).view(sz_b, len_v, n_head, d_v)
        q, k, v = (q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2))
        if mask is not None:
            mask = mask.unsqueeze(1)
        q, attn = self.attention(q, k, v, mask=mask)
        q = q.transpose(1, 2).contiguous().view(sz_b, len_q, -1)
        q = self.fc(q)
        q += residual
        q = self.layer_norm(q)
        return (q, attn)


INIT_ARGS = {
    'n_head': 2,
    'd_model': 8,
    'd_k': 4,
    'd_v': 3,
    'dropout': 0.1
}

ARGS = {
    'q': torch.randn(2, 5, 8),
    'k': torch.randn(2, 6, 8),
    'v': torch.randn(2, 6, 8),
    'mask': None
}

if __name__ == '__main__':
    model = MultiHeadAttention(**INIT_ARGS)
    output, attn = model(**ARGS)
    print("Output shape:", output.shape)
    print("Attention shape:", attn.shape)
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 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ScaledDotProductAttention Ran
ran on a synthesized input · constructed an object; no result was computed
googleinterns/ibrnet/ibrnet/mlp_network.py
code served (permissive licence) · get_code("4f0dc5fabdb8568d")
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, ScaledDotProductAttention: 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)

# ScaledDotProductAttention.__init__ parameters:
# - temperature: float or int
# - attn_dropout: float (default 0.1, but not used in forward)

# ScaledDotProductAttention.forward parameters:
# - q: tensor of shape (batch, ..., seq_len, d_k)
# - k: tensor of shape (batch, ..., seq_len, d_k)
# - v: tensor of shape (batch, ..., seq_len, d_v)
# - mask: optional tensor for masking attention

# Create tensors with distinct dimensions for clarity
batch_size = 2
num_heads = 3
seq_len_q = 5
seq_len_k = 4
d_k = 6
d_v = 7

# q: (batch, num_heads, seq_len_q, d_k)
q = torch.randn(batch_size, num_heads, seq_len_q, d_k)

# k: (batch, num_heads, seq_len_k, d_k)
k = torch.randn(batch_size, num_heads, seq_len_k, d_k)

# v: (batch, num_heads, seq_len_k, d_v)
v = torch.randn(batch_size, num_heads, seq_len_k, d_v)

# mask: (batch, num_heads, seq_len_q, seq_len_k) with 0s and 1s
mask = torch.ones(batch_size, num_heads, seq_len_q, seq_len_k)

# temperature parameter
temperature = 8.0

ARGS = {
    "temperature": temperature,
    "attn_dropout": 0.1,
}

# For forward pass, we also need to prepare inputs
# Store them separately to show how to call forward
FORWARD_ARGS = {
    "q": q,
    "k": k,
    "v": v,
    "mask": mask,
}
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 ScaledDotProductAttention — 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 ScaledDotProductAttention 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
fused_mean_variance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
googleinterns/ibrnet/ibrnet/mlp_network.py
code served (permissive licence) · get_code("34ea5f2db980a0f7")
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 4, 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)

# Construct tensors for fused_mean_variance
# The function operates on x and weight with dim=2
# x shape: (batch, features, sequence_length) = (2, 4, 3)
# weight shape: must be broadcastable, typically (2, 4, 3) or (1, 1, 3)

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

ARGS = {
    "x": x,
    "weight": weight,
}
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 4, 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
weights_init Not yet run
unverified (harvested, no recorded run)
googleinterns/ibrnet/ibrnet/mlp_network.py
code served (permissive licence) · get_code("80f5f942bcddc067")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 1 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
fused_mean_variance
brick of this paper's assembly: helper
4 other papers
4 later · 1 only as an assembly brick
2303.13014 (2023-03)
Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
2306.06359 (2023-06)
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
2308.13897 (2023-08)
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
and 1 more not named here
weights_init
brick of this paper's assembly: helper
3 other papers
3 later · 3 only as an assembly brick
2103.15595 (2021-03)
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
2303.13014 (2023-03)
Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
2308.13897 (2023-08)
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
MultiHeadAttention
brick of this paper's assembly: helper
2 other papers
2 later
2103.15595 (2021-03)
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
2303.13014 (2023-03)
Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
ScaledDotProductAttention
brick of this paper's assembly: helper
2 other papers
2 later
2103.15595 (2021-03)
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
2303.13014 (2023-03)
Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention

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 present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spatial locations and 2D viewing directions), drawing appearance information on the fly from multiple source views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering (IBR), and allows us to render high-resolution imagery. Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes. We render images using classic volume rendering, which is fully differentiable and allows us to train using only multiview posed images as supervision. Experiments show that our method outperforms recent novel view synthesis methods that also seek to generalize to novel scenes. Further, if fine-tuned on each scene, our method is competitive with state-of-the-art single-scene neural rendering methods. 1

For agents

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

get_harvested_code_for_paper("2102.13090")
get_code_for_paper("2102.13090")
have("2102.13090")

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

curl https://syntology.ai/api/ran/2102.13090.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.13090.svg)](https://syntology.ai/paper/2102.13090)

Connect an agent — have() is free.