SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.10970 · ICLR · 2023

Differentiable Rendering with Reparameterized Volume Sampling

Dmitry Vetrov, Kirill Struminsky, Denis Rakitin, Nikita Morozov, Oleg Desheulin

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 2 failures of our instrument; 2 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/2302.10970.json · badge: /api/ran/2302.10970.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
greatdrake/reparameterized-volume-sampling canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
yenchenlin/nerf-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Density Ran
ran on a synthesized input · constructed an object; no result was computed
greatdrake/reparameterized-volume-sampling/nerf/spline.py
code served (permissive licence) · get_code("95a12d3ebef8f6c7")
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, Density: 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

torch.manual_seed(0)

# Create spline knots and density values
# t: spline knots of shape (..., n_knots)
# s: knot density values of shape (..., n_knots)

n_knots = 5
batch_size = 2

# Create knots (sorted, increasing)
t = torch.linspace(0, 10, n_knots).unsqueeze(0).expand(batch_size, -1)

# Create density values (positive for density)
s = torch.ones(batch_size, n_knots) + torch.linspace(0, 1, n_knots).unsqueeze(0)

ARGS = {
    't': t,
    's': s,
}
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 Density — 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 Density 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
batchify Ran
ran; our contract draft was wrong, not the code
greatdrake/reparameterized-volume-sampling/nerf/run_nerf.py
code served (permissive licence) · get_code("fd57e365830d09de")
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 function. 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 a simple function that processes batches
def simple_fn(inputs):
    """A simple function that takes a tensor and returns a processed tensor."""
    return inputs * 2

# Create a small input tensor (batch_size=4, features=3)
input_tensor = torch.randn(4, 3)

# Define chunk size for batching
chunk_size = 2

ARGS = {
    "fn": simple_fn,
    "chunk": chunk_size
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
run_network Ran
ran; our contract draft was wrong, not the code
greatdrake/reparameterized-volume-sampling/nerf/run_nerf.py
code served (permissive licence) · get_code("8f235fb889b93174")
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, 3, 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
import torch.nn as nn

torch.manual_seed(0)

# Create a simple embedding function
def embed_fn(x):
    # x shape: [N, 3] -> output [N, 8]
    return torch.randn(x.shape[0], 8)

# Create a simple view direction embedding function
def embeddirs_fn(x):
    # x shape: [N, 3] -> output [N, 4]
    return torch.randn(x.shape[0], 4)

# Create a simple network that takes embedded inputs and outputs values
class SimpleNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        # Input: 8 (from embed_fn) + 4 (from embeddirs_fn) = 12
        self.linear = nn.Linear(12, 3)
    
    def forward(self, x):
        return self.linear(x)

fn = SimpleNetwork()

# Create inputs tensor: [batch=2, spatial=3, feature=3]
inputs = torch.randn(2, 3, 3)

# Create viewdirs tensor: [batch=2, feature=3]
viewdirs = torch.randn(2, 3)

ARGS = {
    "inputs": inputs,
    "viewdirs": viewdirs,
    "fn": fn,
    "embed_fn": embed_fn,
    "embeddirs_fn": embeddirs_fn,
    "netchunk": 1024 * 64
}
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, 3, 3) — shape (2, 3, 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
batchify_rays Not yet run
unverified (harvested, no recorded run)
greatdrake/reparameterized-volume-sampling/nerf/run_nerf.py
code served (permissive licence) · get_code("44d27aa7d65655b5")
How it ran

no invocation recorded.

batchify_rays Not yet run
unverified (harvested, no recorded run)
yenchenlin/nerf-pytorch/run_nerf.py
code served (permissive licence) · get_code("b0ddc73a6106f3b5")
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 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 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
batchify 17 other papers
11 dated earlier, 6 later
2003.08934 (2020-03)
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
2102.07064 (2021-02)
NeRF--: Neural Radiance Fields Without Known Camera Parameters
2104.04073 (2021-04)
Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
and 14 more not named here
run_network 11 other papers
8 dated earlier, 3 later
2003.08934 (2020-03)
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
2102.07064 (2021-02)
NeRF--: Neural Radiance Fields Without Known Camera Parameters
2104.04073 (2021-04)
Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
and 8 more not named here
batchify_rays 6 other papers
5 dated earlier, 1 same year, order not determinable
2003.08934 (2020-03)
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
2107.02791 (2021-07)
Depth-supervised NeRF: Fewer Views and Faster Training for Free
2201.05989 (2022-01)
Instant neural graphics primitives with a multiresolution hash encoding
and 3 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

In view synthesis, a neural radiance field approximates underlying density and radiance fields based on a sparse set of scene pictures. To generate a pixel of a novel view, it marches a ray through the pixel and computes a weighted sum of radiance emitted from a dense set of ray points. This rendering algorithm is fully differentiable and facilitates gradient-based optimization of the fields. However, in practice, only a tiny opaque portion of the ray contributes most of the radiance to the sum. We propose a simple end-toend differentiable sampling algorithm based on inverse transform sampling. It generates samples according to the probability distribution induced by the density field and picks non-transparent points on the ray. We utilize the algorithm in two ways. First, we propose a novel rendering approach based on Monte Carlo estimates. This approach allows for evaluating and optimizing a neural radiance field with just a few radiance field calls per ray. Second, we use the sampling algorithm to modify the hierarchical scheme proposed in the original NeRF work. We show that our modification improves reconstruction quality of hierarchical models, at the same time simplifying the training procedure by removing the need for auxiliary proposal network losses.

For agents

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

get_harvested_code_for_paper("2302.10970")
get_code_for_paper("2302.10970")
have("2302.10970")

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

curl https://syntology.ai/api/ran/2302.10970.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.10970.svg)](https://syntology.ai/paper/2302.10970)

Connect an agent — have() is free.