SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04101 · CVPR · 2024

How Far Can We Compress Instant-NGP-Based NeRF?

Mehrtash Harandi, Yihang Chen, Qianyi Wu, Jianfei Cai

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 0 have no contract verdict; 3 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/2406.04101.json · badge: /api/ran/2406.04101.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
YihangChen-ee/CNC canonical (classifier label)
classifier basis: census
3 ran · 8 no recorded run
FunctionStatusWhere it lives
get_proposal_requires_grad_fn Ran
ran; our contract draft was wrong, not the code
YihangChen-ee/CNC/nerfacc/estimators/prop_net.py
code served (permissive licence) · get_code("4f3a4cf087c729cb")
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 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 numpy as np

# Define ARGS dictionary with valid arguments for get_proposal_requires_grad_fn
ARGS = {
    "target": 5.0,
    "num_steps": 1000,
}
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 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
inclusive_prod Ran
ran; our contract draft was wrong, not the code
YihangChen-ee/CNC/nerfacc/scan.py
code served (permissive licence) · get_code("a2f65b69f49d6296")
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 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Case 1: Without packed_info - simple N-D tensor case
inputs_simple = torch.tensor([1., 2., 3., 4.])

# Case 2: With packed_info - flattened tensor case
inputs_flattened = torch.tensor([1., 2., 3., 4., 5., 6., 7., 8., 9.], dtype=torch.float32)
packed_info = torch.tensor([[0, 2], [2, 3], [5, 4]], dtype=torch.long)

# We'll use the simple case (without packed_info) since the custom CUDA kernels (_C module)
# won't be available in CPU-only environment anyway
ARGS = {
    "inputs": inputs_simple,
    "packed_info": None
}
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 1, dtype family float, shape (4,) — shape (4,) 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
inclusive_sum Ran
ran; our contract draft was wrong, not the code
YihangChen-ee/CNC/nerfacc/scan.py
code served (permissive licence) · get_code("b11cf9a1bce32098")
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, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Case 1: packed_info is None - use N-D tensor
inputs_nd = torch.tensor([[1., 2., 3.], [4., 5., 6.]], dtype=torch.float32)
packed_info_none = None

ARGS = {
    "inputs": inputs_nd,
    "packed_info": packed_info_none,
}
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, 3) — shape (2, 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
exclusive_sum Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/scan.py
code served (permissive licence) · get_code("7e3dcf7024983727")
How it ran

no invocation recorded.

opencv_lens_undistortion Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/cameras.py
code served (permissive licence) · get_code("f80c8a6f512f2a64")
How it ran

no invocation recorded.

opencv_lens_undistortion_fisheye Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/cameras.py
code served (permissive licence) · get_code("701af0924cbf9bc7")
How it ran

no invocation recorded.

pack_info Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/pack.py
code served (permissive licence) · get_code("2319e61f724594d5")
How it ran

no invocation recorded.

ray_aabb_intersect Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/grid.py
code served (permissive licence) · get_code("98893c67b549e0d9")
How it ran

no invocation recorded.

render_transmittance_from_alpha Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/volrend.py
code served (permissive licence) · get_code("250d0f7b88ba69e7")
How it ran

no invocation recorded.

render_transmittance_from_density Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/volrend.py
code served (permissive licence) · get_code("96c9d934bd45d19e")
How it ran

no invocation recorded.

rendering Not yet run
unverified (harvested, no recorded run)
YihangChen-ee/CNC/nerfacc/volrend.py
code served (permissive licence) · get_code("c21221ab7ee5e5e2")
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

In recent years, Neural Radiance Field (NeRF) has demonstrated remarkable capabilities in representing 3D scenes. To expedite the rendering process, learnable explicit representations have been introduced for combination with implicit NeRF representation, which however results in a large storage space requirement. In this paper, we introduce the Context-based NeRF Compression (CNC) framework, which leverages highly efficient context models to provide a storage-friendly NeRF representation. Specifically, we excavate both level-wise and dimension-wise context dependencies to enable probability prediction for information entropy reduction. Additionally, we exploit hash collision and occupancy grids as strong prior knowledge for better context modeling. To the best of our knowledge, we are the first to construct and exploit context models for NeRF compression. We achieve a size reduction of 100⇥ and 70⇥ with improved fidelity against the baseline Instant-NGP on Synthesic-NeRF and Tanks and Temples datasets, respectively. Additionally, we attain 86.7% and 82.3% storage size reduction against the SOTA NeRF compression method BiRF. Our code is available here: https://github.com/YihangChen-ee/CNC.

For agents

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

get_harvested_code_for_paper("2406.04101")
get_code_for_paper("2406.04101")
have("2406.04101")

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

curl https://syntology.ai/api/ran/2406.04101.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.04101.svg)](https://syntology.ai/paper/2406.04101)

Connect an agent — have() is free.