Papers › SMITE: Segment Me In TimE

SMITE: Segment Me In TimE

24 Oct 2024arXiv:2410.18538archive 2025-07-28

Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki, Andrea Tagliasacchi, Ghassan Hamarneh, Ali Mahdavi Amiri

Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty increases when the segmentation is with arbitrary granularity, meaning the number of segments can vary arbitrarily, and masks are defined based on only one or a few sample images. In this paper, we address this issue by employing a pre-trained text to image diffusion model supplemented with an additional tracking mechanism. We demonstrate that our approach can effectively manage various segmentation scenarios and outperforms state-of-the-art alternatives.

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 21 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 14 ran (4 with no instrument failure; 10 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

alimohammadiamirhossein/smite officialmentioned on GitHubpytorchSyntology: 21 samples, 14 ran (10 instrument-failed) · 7 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

21 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 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.

4ran · honoured contract
8ran · our draft was wrong
2ran; the contract check could not run
7unverified

Licence: 0 of the 21 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 alimohammadiamirhossein/smite. “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.

alimohammadiamirhossein/smite official repository 21 samples, 14 ran (10 instrument-failed) · 7 unverified
_calculate_pixel_weights src/latent_optimization.py ran · our draft was wrong Apache-2.0 (permissive) · 7227bc7182f55a3b · report fixture: signature pipeline:callable/0/?, was_tracked:Tensor/2/float · returned Tensor · level recorded 2026-09-22
_compute_loss src/latent_optimization.py ran · honoured contract Apache-2.0 (permissive) · 01aa7ec519d76e3b · report fixture: signature pipeline:callable/0/?, latents_dict:dict/0/?, was_dst:Tensor/5/float, kwargs:dict/0/? · returned tuple · level recorded 2026-09-22
_compute_refrence_loss src/latent_optimization.py ran · our draft was wrong Apache-2.0 (permissive) · a40ca276c0314b43 · report fixture: signature was_dst:Tensor/4/float, was_refrence:Tensor/4/float, kwargs:dict/0/? · returned Tensor · level recorded 2026-09-22
_compute_tracking_loss src/latent_optimization.py ran · our draft was wrong Apache-2.0 (permissive) · be631dd6f50039f2 · report fixture: signature was_dst:Tensor/2/float, was_tracked:Tensor/2/float, pipeline:callable/0/? · returned Tensor · level recorded 2026-09-22
_process_timestep src/latent_optimization.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 (permissive) · 76eb30418deb0324 · report fixture: signature pipeline:callable/0/?, prompt_embeds:Tensor/3/float, latents:Tensor/4/float, depth_input:Tensor/4/float, t:int/0/int, attention_output_size:int/0/int, token_ids:list/1/int, average_layers:bool/0/bool, apply_softmax:bool/0/bool, video_length:int/0/int, guidance_scale:float/0/float, cross_attention_kwargs:dict/0/?, controlnet_keep:Tensor/1/float, controlnet_conditioning_scale:float/0/float, extra_step_kwargs:dict/0/?, return_latent:bool/0/bool · returned tuple · level recorded 2026-09-22
_update_moments src/latent_optimization.py ran · honoured contract Apache-2.0 (permissive) · 3c743feea5734a20 · report fixture: signature grad_cond:Tensor/0/float, m1:Tensor/0/float, m2:Tensor/0/float, iter_:int/0/int · returned tuple · level recorded 2026-09-22
calculate_controlnet_features src/latent_optimization.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 (permissive) · 0cb10cbe5854515a · report fixture: signature pipeline:MockPipeline/0/?, depth:Tensor/2/float, latent_model_input:Tensor/2/float, prompt_embeds:Tensor/2/float, timestep:int/0/int, controlnet_keep:list/1/float, controlnet_conditioning_scale:float/0/float · returned tuple · level recorded 2026-09-22
calculate_new_was_value src/latent_optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · b8df771e20c60389 · report fixture: signature feats:Tensor/2/float · returned Tensor · level recorded 2026-09-22
colorize_depth_maps src/latent_optimization.py ran · our draft was wrong Apache-2.0 (permissive) · b5c8182dd8640ec2 · report fixture: signature depth_map:Tensor/3/float, min_depth:float/0/float, max_depth:float/0/float, cmap:str/0/str, valid_mask:Tensor/3/bool · returned Tensor · level recorded 2026-09-22
create_slices src/latent_optimization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 4cb5f2bdcabf144d · report fixture: signature length:int/0/int, slice_size:int/0/int · returned list · level recorded 2026-09-22
dct_loss src/latent_optimization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fe6f43be61a8c67d · report fixture: signature feat_pred:Tensor/4/float, feat_gt:Tensor/4/float, low_pass:bool/0/bool, threshold:float/0/float · returned tuple · level recorded 2026-09-22
dct_low_pass_filter src/latent_optimization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d5f0c2ad9c03b52a · report fixture: signature dct_coefficients:Tensor/5/float, percentage:float/0/float · returned Tensor · level recorded 2026-09-22
determine_window src/latent_optimization.py ran · honoured contract Apache-2.0 (permissive) · ad464697812cba58 · report fixture: signature index:int/0/int, length:int/0/int, window_size:int/0/int · returned tuple · level recorded 2026-09-22
gather_features in 78 papers src/latent_optimization.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · bec020dc9147bb3b · report fixture: signature was:Tensor/4/float, pred_track_indice:Tensor/3/int, pred_visibility:Tensor/2/float, i:int/0/int, k:int/0/int, start:int/0/int, end:int/0/int · returned Tensor · level recorded 2026-09-22
_optimize_a_slice src/latent_optimization.py unverified Apache-2.0 (permissive) · 18387f7bb11f3441 · report
_update_latent_with_energy_function src/latent_optimization.py unverified Apache-2.0 (permissive) · 996cce05a83e5dc3 · report
_update_latent_with_gradient src/latent_optimization.py unverified Apache-2.0 (permissive) · 8de285a460a7632e · report
_visualization_during_optimization src/latent_optimization.py unverified Apache-2.0 (permissive) · 0997043fb02a185a · report
apply_voting src/latent_optimization.py unverified Apache-2.0 (permissive) · a355f21b2457d26e · report
optimize_latents src/latent_optimization.py unverified Apache-2.0 (permissive) · 2942ddefa7ca0a88 · report
visualize_attention_maps src/latent_optimization.py unverified Apache-2.0 (permissive) · ef527e7f7a4c8410 · 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 SMITE (graph method: SMITE). 21 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. optimize_latents entry · level 0 · unverified · 2942ddefa7ca0a88
  2. _optimize_a_slice helper · level 0 · unverified · 18387f7bb11f3441
  3. _visualization_during_optimization helper · level 0 · unverified · 0997043fb02a185a
  4. apply_voting helper · level 0 · unverified · a355f21b2457d26e
  5. create_slices helper · level 1 · ran · our draft was wrong · 4cb5f2bdcabf144d
  6. _update_latent_with_energy_function update_rule · level 0 · unverified · 996cce05a83e5dc3
  7. dct_loss helper · level 1 · ran · our draft was wrong · fe6f43be61a8c67d
  8. visualize_attention_maps helper · level 0 · unverified · ef527e7f7a4c8410
  9. calculate_new_was_value helper · level 1 · ran · honoured contract · b8df771e20c60389
  10. determine_window helper · level 1 · ran · honoured contract · ad464697812cba58
  11. gather_features helper · level 1 · ran · our draft was wrong · bec020dc9147bb3b
  12. _compute_loss loss · level 1 · ran · honoured contract · 01aa7ec519d76e3b
  13. _process_timestep helper · level 1 · ran; the contract check could not run (RAISES) · 76eb30418deb0324
  14. _update_latent_with_gradient update_rule · level 0 · unverified · 8de285a460a7632e
  15. dct_low_pass_filter helper · level 1 · ran · our draft was wrong · d5f0c2ad9c03b52a
  16. colorize_depth_maps helper · level 1 · ran · our draft was wrong · b5c8182dd8640ec2
  17. _compute_refrence_loss loss · level 1 · ran · our draft was wrong · a40ca276c0314b43
  18. _compute_tracking_loss loss · level 1 · ran · our draft was wrong · be631dd6f50039f2
  19. calculate_controlnet_features helper · level 1 · ran; the contract check could not run (RAISES) · 0cb10cbe5854515a
  20. _update_moments update_rule · level 1 · ran · honoured contract · 3c743feea5734a20
  21. _calculate_pixel_weights helper · level 1 · ran · our draft was wrong · 7227bc7182f55a3b

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="2410.18538") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

SegmentationSemantic SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic Segmentation

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