Papers › CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

19 Oct 2022arXiv:2210.10716archive 2025-07-28

Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas, Romain Brégier, Yohann Cabon, Vaibhav Arora, Leonid Antsfeld, Boris Chidlovskii, Gabriela Csurka, Jérôme Revaud

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-art performance when finetuned for high-level semantic tasks, e.g. image classification and object detection. In this paper we instead seek to learn representations that transfer well to a wide variety of 3D vision and lower-level geometric downstream tasks, such as depth prediction or optical flow estimation. Inspired by MIM, we propose an unsupervised representation learning task trained from pairs of images showing the same scene from different viewpoints. More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image. In single-view MIM, the masked content often cannot be inferred precisely from the visible portion only, so the model learns to act as a prior influenced by high-level semantics. In contrast, this ambiguity can be resolved with cross-view completion from the second unmasked image, on the condition that the model is able to understand the spatial relationship between the two images. Our experiments show that our pretext task leads to significantly improved performance for monocular 3D vision downstream tasks such as depth estimation. In addition, our model can be directly applied to binocular downstream tasks like optical flow or relative camera pose estimation, for which we obtain competitive results without bells and whistles, i.e., using a generic architecture without any task-specific design.

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 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (8 with no instrument failure; 4 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

naver/croco officialmentioned on GitHubpytorchSyntology: 15 samples, 12 ran (4 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

15 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 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 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 · our draft was wrong
3ran; the contract check could not run
8ran
3unverified

Licence: 15 of the 15 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 naver/croco. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

naver/croco official repository 15 samples, 12 ran (4 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · e43d66926c52d73f · report fixture: returned Attention · level recorded 2026-09-22
CrossAttention in 85 papers models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · 863ed6dfef2b047a · report fixture: returned CrossAttention · level recorded 2026-09-22
DecoderBlock in 30 papers models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · 1615adbdcbbbfe4f · report fixture: returned DecoderBlock · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
models/croco.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 99b1932affbf5fdf · report fixture: returned DropPath · level recorded 2026-09-22
Mlp in 102 papers models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · 001c4e1dde23a54e · report fixture: returned Mlp · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · 20f0e8a44c49e22d · report fixture: returned PatchEmbed · level recorded 2026-09-22
PositionGetter models/croco.py ran licence not identified · pointer only · 3325c483d48e12ee · report fixture: signature b:int/0/int, h:int/0/int, w:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-24
RandomMask models/croco.py ran · metamorphic tier: deterministic licence not identified · pointer only · fe5195c3233da136 · report fixture: returned RandomMask · level recorded 2026-09-22
_ntuple in 17 papers models/croco.py ran · our draft was wrong licence not identified · pointer only · cd4d36b9126e53f2 · report fixture: signature n:int/0/int · returned function · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/croco.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · f9a1900525331e0f · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool, scale_by_keep:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float64
models/croco.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 4bdd36eab04c3f62 · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers models/croco.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence not identified · pointer only · d9a2bb7a053e82c0 · report fixture: signature embed_dim:int/0/int, grid_size:tuple/1/int, n_cls_token:int/0/int · returned ndarray · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/croco.py unverified licence not identified · pointer only · d98a51333a14237d · report
CroCoNet models/croco.py unverified licence not identified · pointer only · f473b33a00269412 · report
get_2d_sincos_pos_embed_from_grid in 140 papers models/croco.py unverified licence not identified · pointer only · 4fd80de79832745d · 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 CroCo (graph method: CroCo). 15 bricks; individually on a fixture: 12 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. CroCoNet entry · level 0 · unverified · f473b33a00269412
  2. Block model · level 0 · unverified · d98a51333a14237d
  3. DecoderBlock model · level 1 · ran · 1615adbdcbbbfe4f
  4. PatchEmbed model · level 1 · ran · 20f0e8a44c49e22d
  5. RandomMask helper · level 1 · ran · fe5195c3233da136
  6. get_2d_sincos_pos_embed helper · level 1 · ran; the contract check could not run (RAISES) · d9a2bb7a053e82c0
  7. Attention model · level 1 · ran · e43d66926c52d73f
  8. DropPath model · level 1 · ran · 99b1932affbf5fdf
  9. Mlp model · level 1 · ran · 001c4e1dde23a54e
  10. drop_path helper · level 1 · ran; the contract check could not run (RAISES) · f9a1900525331e0f
  11. CrossAttention model · level 1 · ran · 863ed6dfef2b047a
  12. PositionGetter helper · level 1 · ran · 3325c483d48e12ee
  13. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 4fd80de79832745d
  14. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run (RAISES) · 4bdd36eab04c3f62
  15. _ntuple helper · level 1 · ran · our draft was wrong · cd4d36b9126e53f2

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="2210.10716") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Camera Pose EstimationDepth EstimationDepth PredictionImage ClassificationObject DetectionOptical Flow EstimationPose EstimationRepresentation Learningimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MIM

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