Papers › Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

3 Nov 2022arXiv:2211.02048archive 2025-07-28

Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, Song Han, Jun-Yan Zhu

During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models. Our key observation is that users prone to gradually edit the input image. This motivates us to cache and reuse the feature maps of the original image. Given an edited image, we sparsely apply the convolutional filters to the edited regions while reusing the cached features for the unedited areas. Based on our algorithm, we further propose Sparse Incremental Generative Engine (SIGE) to convert the computation reduction to latency reduction on off-the-shelf hardware. With about 1%-area edits, SIGE accelerates DDPM by 3.0× on NVIDIA RTX 3090 and 4.6× on Apple M1 Pro GPU, Stable Diffusion by 7.2× on 3090, and GauGAN by 5.6× on 3090 and 5.2× on M1 Pro GPU. Compared to our conference version, we extend SIGE to accommodate attention layers and apply it to Stable Diffusion. Additionally, we offer support for Apple M1 Pro GPU and include more results with large and sequential edits.

PaperPDFCodeCode Syntology ranMethod as code

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 17 code samples harvested from 1 repository linked to this paper: 6 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; 1 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lmxyy/sige officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 6 ran (1 instrument-failed) · 11 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

17 samples harvested: 6 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; 1 where Syntology's instrument failed) · 11 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
5ran
11unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lmxyy/sige. “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.

lmxyy/sige official repository 17 samples, 6 ran (1 instrument-failed) · 11 unverified
Downsample in 58 papers diffusion/models/ddpm_arch/sige_fused_unet.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 7a0f92aace8379bd · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SIGEConv2d diffusion/models/ddpm_arch/sige_fused_unet.py ran fingerprinted licence not identified · pointer only · 335c75661060896d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
SIGEModule diffusion/models/ddpm_arch/sige_fused_unet.py ran licence not identified · pointer only · d507545007f66e19 · report fixture: signature masks:dict/0/?, cache:dict/0/?, timestamp:int/0/int · returned NoneType · level recorded 2026-09-24
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
diffusion/models/ddpm_arch/sige_fused_unet.py ran; the contract check could not run (RAISES) licence not identified · pointer only · b8dedf14898e5502 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded 2026-09-22
my_group_norm diffusion/models/ddpm_arch/sige_fused_unet.py ran licence not identified · pointer only · 1dc30e6b525d42ae · report fixture: signature x:Tensor/4/float, norm:callable/0/? · returned tuple · level recorded 2026-09-25
reduce_mask diffusion/models/ddpm_arch/sige_fused_unet.py ran licence not identified · pointer only · 153647897a024a30 · report fixture: signature mask:Tensor/2/float, block_size:int/0/int, stride:int/0/int, padding:int/0/int, verbose:bool/0/bool · returned Tensor · level recorded 2026-09-25
Gather diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · e6819730eb3cbd0f · report
SIGEDownsample diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 5fd30a8dc69ba054 · report
SIGEFusedAttnBlock diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · ab08502e82055fad · report
SIGEFusedResnetBlock diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 4f54fe4195f44e4a · report
SIGEFusedUNet diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 045129cab1cb8c3a · report
SIGEModel diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 024f482cc587c98d · report
SIGEModuleWrapper diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 8a575c88399bbcf7 · report
SIGEUpsample diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · f153297ee40e8b8d · report
Scatter diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · aae8fcf6a37d95da · report
ScatterGather diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · c3a4f27f51286763 · report
ScatterWithBlockResidual diffusion/models/ddpm_arch/sige_fused_unet.py unverified licence not identified · pointer only · 198eb290f706c5a3 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Spatially Sparse Inference (SSI) (graph method: Spatially Sparse Inference (SSI)). 19 bricks; individually on a fixture: 8 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; 3 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. SIGEFusedUNet entry · level 0 · unverified · 045129cab1cb8c3a
  2. Downsample helper · level 1 · ran · 7a0f92aace8379bd
  3. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  4. SIGEDownsample model · level 0 · unverified · 5fd30a8dc69ba054
  5. SIGEFusedAttnBlock model · level 0 · unverified · ab08502e82055fad
  6. SIGEFusedResnetBlock model · level 0 · unverified · 4f54fe4195f44e4a
  7. SIGEModel helper · level 0 · unverified · 024f482cc587c98d
  8. SIGEUpsample model · level 0 · unverified · f153297ee40e8b8d
  9. get_timestep_embedding helper · level 1 · ran; the contract check could not run (RAISES) · b8dedf14898e5502
  10. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c
  11. Gather helper · level 0 · unverified · e6819730eb3cbd0f
  12. SIGEModule helper · level 1 · ran · d507545007f66e19
  13. Scatter helper · level 0 · unverified · aae8fcf6a37d95da
  14. SIGEConv2d helper · level 1 · ran · 335c75661060896d
  15. my_group_norm helper · level 1 · ran · 1dc30e6b525d42ae
  16. ScatterGather helper · level 0 · unverified · c3a4f27f51286763
  17. ScatterWithBlockResidual helper · level 0 · unverified · 198eb290f706c5a3
  18. reduce_mask helper · level 1 · ran · 153647897a024a30
  19. SIGEModuleWrapper helper · level 0 · unverified · 8a575c88399bbcf7

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2211.02048") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSPEED

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