Papers › Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via...

Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance

17 Dec 2024arXiv:2412.12974archive 2025-07-28

Wenhao Sun, Benlei Cui, Xue-Mei Dong, Jingqun Tang

Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as generating random artifacts and the incapacity to repaint foreground object areas with appropriate content after removal. To tackle these problems, we propose Attentive Eraser, a tuning-free method to empower pre-trained diffusion models for stable and effective object removal. Firstly, in light of the observation that the self-attention maps influence the structure and shape details of the generated images, we propose Attention Activation and Suppression (ASS), which re-engineers the self-attention mechanism within the pre-trained diffusion models based on the given mask, thereby prioritizing the background over the foreground object during the reverse generation process. Moreover, we introduce Self-Attention Redirection Guidance (SARG), which utilizes the self-attention redirected by ASS to guide the generation process, effectively removing foreground objects within the mask while simultaneously generating content that is both plausible and coherent. Experiments demonstrate the stability and effectiveness of Attentive Eraser in object removal across a variety of pre-trained diffusion models, outperforming even training-based methods. Furthermore, Attentive Eraser can be implemented in various diffusion model architectures and checkpoints, enabling excellent scalability. Code is available at https://github.com/Anonym0u3/AttentiveEraser.

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 13 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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.

anonym0u3/attentiveeraser officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 9 ran (2 instrument-failed) · 4 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

13 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 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.

1ran · violated contract
2ran · our draft was wrong
6ran
4unverified

Licence: 0 of the 13 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 anonym0u3/attentiveeraser. “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.

anonym0u3/attentiveeraser official repository 13 samples, 9 ran (2 instrument-failed) · 4 unverified
Fourier_filter in 6 papers utils.py ran Apache-2.0 (permissive) · 4c4fb4372c440cb1 · report fixture: signature x_in:Tensor/4/float, threshold:int/0/int, scale:float/0/float · returned Tensor · level recorded 2026-09-25
ceil_modulo evaluation/lpips_score.py ran fingerprinted Apache-2.0 (permissive) · c925ce390296992d · report fixture: signature x:int/0/int, mod:int/0/int · returned int · level recorded 2026-09-25
isinstance_str in 12 papers utils.py ran · violated contract Apache-2.0 (permissive) · cd5d5067de871c97 · report fixture: signature x:DerivedClass/0/?, cls_name:str/0/str · returned bool · level recorded 2026-09-22
l2 in 38 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
evaluation/lpips.py ran fingerprinted Apache-2.0 (permissive) · cebd4a767f96722b · report fixture: signature p0:ndarray/2/float, p1:ndarray/2/float, range:float/0/float · returned float32 · level recorded 2026-09-25
load_image in 273 papers evaluation/lpips_score.py ran Apache-2.0 (permissive) · e6809c12159dbf7b · report fixture: signature fname:str/0/str, mode:str/0/str, eval_resolution:int/0/int, return_orig:bool/0/bool · returned ndarray · level recorded 2026-09-25
move_to_device in 26 papers evaluation/lpips_score.py ran · our draft was wrong Apache-2.0 (permissive) · b30cecbde78e6922 · report fixture: signature obj:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-25
normalize_tensor in 47 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
evaluation/lpips.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 15df2c2c65353c11 · report fixture: signature in_feat:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-25
pad_img_to_modulo AAS/data.py ran fingerprinted Apache-2.0 (permissive) · 5db84139b1c887ad · report fixture: signature img:ndarray/3/float, mod:int/0/int · returned ndarray · level recorded 2026-09-25
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
evaluation/lpips.py ran fingerprinted Apache-2.0 (permissive) · e844cf206c6621e3 · report fixture: signature p0:ndarray/2/float, p1:ndarray/2/float, peak:float/0/float · returned float32 · level recorded 2026-09-25
get_frechet_inception_distance evaluation/fid.py unverified Apache-2.0 (permissive) · 9a3ae445a49ae8f0 · report
pad_tensor_to_modulo AAS/data.py unverified Apache-2.0 (permissive) · 223f8559389c0619 · report
regiter_attention_editor_diffusers in 6 papers AAS/AAS_utils.py unverified Apache-2.0 (permissive) · d321812b8f73ef4b · report
regiter_attention_editor_ldm in 5 papers AAS/AAS_utils.py unverified Apache-2.0 (permissive) · 431f768e76ae86fa · report

Tasks

Image GenerationObject

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDiffusionSoftmax

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