Papers › Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model

Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model

9 Jun 2023arXiv:2306.05720archive 2025-07-28

Yida Chen, Fernanda Viégas, Martin Wattenberg

Latent diffusion models (LDMs) exhibit an impressive ability to produce realistic images, yet the inner workings of these models remain mysterious. Even when trained purely on images without explicit depth information, they typically output coherent pictures of 3D scenes. In this work, we investigate a basic interpretability question: does an LDM create and use an internal representation of simple scene geometry? Using linear probes, we find evidence that the internal activations of the LDM encode linear representations of both 3D depth data and a salient-object / background distinction. These representations appear surprisingly early in the denoising process-well before a human can easily make sense of the noisy images. Intervention experiments further indicate these representations play a causal role in image synthesis, and may be used for simple high-level editing of an LDM's output. Project page: https://yc015.github.io/scene-representation-diffusion-model/

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (5 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yc015/scene-representation-diffusion-model officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 11 ran (6 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
5ran
3unverified

Licence: 5 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yc015/scene-representation-diffusion-model. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yc015/scene-representation-diffusion-model official repository 14 samples, 11 ran (6 instrument-failed) · 3 unverified
check_imports in 15 papers modified_diffusers/dynamic_modules_utils.py ran · our draft was wrong MIT (permissive) · 301682fc3342590a · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
compute_scale_and_shift in 8 papers probe_src/depth_loss.py ran MIT (permissive) here; the stored copy is pointer only · 25ba9b5031480973 · report fixture: signature prediction:Tensor/3/float, target:Tensor/3/float, mask:Tensor/3/float · returned tuple · level recorded 2026-09-24
cosine_distance in 29 papers
census: 5 implementations from 6 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
modified_diffusers/pipelines/stable_diffusion/safety_checker.py ran fingerprinted MIT (permissive) · a580fad941fd2f88 · report fixture: signature image_embeds:Tensor/2/float, text_embeds:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_parameter_device in 18 papers modified_diffusers/modeling_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · eafa252fd6f86857 · report fixture: signature parameter:callable/0/? · returned device · level recorded 2026-09-24
get_parameter_dtype in 20 papers modified_diffusers/modeling_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · dc2045840ce679cb · report fixture: signature parameter:callable/0/? · returned dtype · level recorded 2026-09-24
get_relative_import_files in 28 papers modified_diffusers/dynamic_modules_utils.py ran · our draft was wrong MIT (permissive) · 00cc853a73f3aeb6 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-26
get_relative_imports in 28 papers modified_diffusers/dynamic_modules_utils.py ran · our draft was wrong MIT (permissive) · 450aeffe7f80f917 · report fixture: signature module_file:str/0/str · returned list · level recorded 2026-09-26
make_counterfactual_label probe_src/continuous_depth_intervention_utils.py ran MIT (permissive) · 1090b7fe2da4f983 · report fixture: signature label:ndarray/2/int, angle:int/0/int, translate:list/1/int, scale:float/0/float, sheer:float/0/float, fill:int/0/int · returned Tensor · level recorded 2026-09-26
make_counterfactual_label probe_src/depth_intervention_utils.py ran MIT (permissive) · 002691469b74a353 · report fixture: signature label:ndarray/2/int, angle:int/0/int, translate:list/1/int, scale:float/0/float, sheer:float/0/float, fill:int/0/int · returned Tensor · level recorded 2026-09-26
optimize_one_inter_rep probe_src/continuous_depth_intervention_utils.py ran MIT (permissive) · 16f5f8b292ace798 · report fixture: signature inter_rep:Tensor/2/float, layer_name:str/0/str, target:list/1/float, probe:callable/0/?, lr:float/0/float, max_epoch:int/0/int, loss_func:callable/0/?, smoothness_loss_func:callable/0/?, image:Tensor/2/float, verbose:bool/0/bool · returned Tensor · level recorded 2026-09-26
reduction_batch_based in 6 papers probe_src/depth_loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e8996630fe3501e1 · report fixture: signature image_loss:Tensor/1/float, M:Tensor/1/float · returned Tensor · level recorded 2026-09-24
load_state_dict in 114 papers modified_diffusers/modeling_utils.py unverified MIT (permissive) · 77bd5e6e8ca8c91d · report
optimize_one_inter_rep probe_src/depth_intervention_utils.py unverified MIT (permissive) · b31fe2f42ad6b09d · report
reduction_image_based in 5 papers probe_src/depth_loss.py unverified MIT (permissive) here; the stored copy is pointer only · c92f0115a72bf454 · report

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections