SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.05085 · 2022

Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2206.05085.json · badge: /api/ran/2206.05085.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
sunset1995/torch_efficient_distloss canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
eff_distloss_native Ran
ran, violated the contract we drafted
sunset1995/torch_efficient_distloss/torch_efficient_distloss/eff_distloss.py
code served (permissive licence) · get_code("f9c904315eba1175")
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 the function
B = 2  # batch size
N = 4  # number of sampled points

# w: Float tensor in shape [B,N] - volume rendering weights
w = torch.rand(B, N)

# m: Float tensor in shape [B,N] - midpoint distance to camera
m = torch.rand(B, N)

# interval: Scalar or float tensor in shape [B,N]
interval = torch.rand(B, N)

ARGS = {
    "w": w,
    "m": m,
    "interval": interval,
}
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
get_rays Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sunset1995/directvoxgo
pointer only; the stored copy get_code serves, from sunset1995/directvoxgo, is pointer only (licence: NOASSERTION) · get_code("049307a781780caa")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_rays_np Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from sunset1995/directvoxgo
pointer only; the stored copy get_code serves, from sunset1995/directvoxgo, is pointer only (licence: NOASSERTION) · get_code("797ecc3ad3e96c73")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

ndc_rays Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sunset1995/directvoxgo
pointer only; the stored copy get_code serves, from sunset1995/directvoxgo, is pointer only (licence: NOASSERTION) · get_code("4366d225ac2fe16d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 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, 3 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
ndc_rays 10 other papers
3 dated earlier, 7 later
2104.04073 (2021-04)
Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
2111.11215 (2021-11)
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
2202.05263 (2022-02)
Block-NeRF: Scalable Large Scene Neural View Synthesis
and 7 more not named here
get_rays 7 other papers
2 dated earlier, 5 later
2111.11215 (2021-11)
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
2202.05263 (2022-02)
Block-NeRF: Scalable Large Scene Neural View Synthesis
2304.12308 (2023-04)
A SUBMISSION TO IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Segment Anything in 3D with Radiance Fields
and 4 more not named here
get_rays_np 5 other papers
1 dated earlier, 4 later
2111.11215 (2021-11)
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
2304.12308 (2023-04)
A SUBMISSION TO IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Segment Anything in 3D with Radiance Fields
2312.06657 (2023-12)
Learning Naturally Aggregated Appearance for Efficient 3D Editing
and 2 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 this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss.

For agents

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

get_harvested_code_for_paper("2206.05085")
get_code_for_paper("2206.05085")
have("2206.05085")

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

curl https://syntology.ai/api/ran/2206.05085.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.05085.svg)](https://syntology.ai/paper/2206.05085)

Connect an agent — have() is free.