SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.16617 · CVPR · 2023

NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination

Changjie Fan, Xin Yu, Yongqiang Zhang, Zhipeng Hu, Lincheng Li, Haoqian Wu

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 1 failure of our instrument; 10 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/2303.16617.json · badge: /api/ran/2303.16617.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
FuxiComputerVision/Nefii marked official in Papers with Code
Papers with Code archive
1 ran · 10 no recorded run
FunctionStatusWhere it lives
sg_fn Ran
ran; our contract draft was wrong, not the code
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("adf4d627bdcffb1f")
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. 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 with distinct dimensions
# upsilon: [..., 3] - input variable, batch size 2
upsilon = torch.randn(2, 3)

# xi: [..., 3] - direction vector, batch size 2
xi = torch.randn(2, 3)

# lamb: [..., 1] - lambda parameter (scalar per batch element), batch size 2
lamb = torch.randn(2, 1)

# mu: [..., 3] - amplitude/color, batch size 2
mu = torch.randn(2, 3)

ARGS = {
    "upsilon": upsilon,
    "xi": xi,
    "lamb": lamb,
    "mu": mu,
}
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
brdf_sampling Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("d4244c3ae5a361a4")
How it ran

no invocation recorded.

cos_sampling Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("51529f43ad262739")
How it ran

no invocation recorded.

get_visibility_and_indirect_light Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("a645b2cc39e343fd")
How it ran

no invocation recorded.

mix_sg_sampling Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("abe83721692e6679")
How it ran

no invocation recorded.

pdf_fn_brdf_gxx Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("9a557f1c2ae33bb5")
How it ran

no invocation recorded.

pdf_fn_cos Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("f98c055fe34ca35c")
How it ran

no invocation recorded.

pdf_fn_mix_sg Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("ed5a49fa28f56245")
How it ran

no invocation recorded.

power_heuristic_list Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("bbe6de7f3c2f0c6c")
How it ran

no invocation recorded.

pt_render_diff_shadow_indirect_mlp Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("9674f28e2905a7cf")
How it ran

no invocation recorded.

rotate_to_normal Not yet run
unverified (harvested, no recorded run)
FuxiComputerVision/Nefii/code/model/path_tracing_render.py
code served (permissive licence) · get_code("3cc3e1222a96630e")
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

Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. In order to achieve better decomposition, recent approaches attempt to model indirect illuminations reflected from different materials via Spherical Gaussians (SG), which, however, tends to blur the high-frequency reflection details. In this paper, we propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images, while considering near-field indirect illumination. In a nutshell, we introduce the Monte Carlo sampling based path tracing and cache the indirect illumination as neural radiance, enabling a physics-faithful and easy-to-optimize inverse rendering method. To enhance efficiency and practicality, we leverage SG to represent the smooth environment illuminations and apply importance sampling techniques. To supervise indirect illuminations from unobserved directions, we develop a novel radiance consistency constraint between implicit neural radiance and path tracing results of unobserved rays along with the joint optimization of materials and illuminations, thus significantly improving the decomposition performance. Extensive experiments demonstrate that our method outperforms the state-of-the-art on multiple synthetic and real datasets, especially in terms of inter-reflection decomposition.

For agents

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

get_harvested_code_for_paper("2303.16617")
get_code_for_paper("2303.16617")
have("2303.16617")

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

curl https://syntology.ai/api/ran/2303.16617.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.16617.svg)](https://syntology.ai/paper/2303.16617)

Connect an agent — have() is free.