Papers › Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

15 Jun 2023NeurIPS 2023 11arXiv:2306.09347archive 2025-07-28

Youquan Liu, Lingdong Kong, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu

Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a novel framework that harnesses VFMs for segmenting diverse automotive point cloud sequences. Seal exhibits three appealing properties: i) Scalability: VFMs are directly distilled into point clouds, obviating the need for annotations in either 2D or 3D during pretraining. ii) Consistency: Spatial and temporal relationships are enforced at both the camera-to-LiDAR and point-to-segment regularization stages, facilitating cross-modal representation learning. iii) Generalizability: Seal enables knowledge transfer in an off-the-shelf manner to downstream tasks involving diverse point clouds, including those from real/synthetic, low/high-resolution, large/small-scale, and clean/corrupted datasets. Extensive experiments conducted on eleven different point cloud datasets showcase the effectiveness and superiority of Seal. Notably, Seal achieves a remarkable 45.0% mIoU on nuScenes after linear probing, surpassing random initialization by 36.9% mIoU and outperforming prior arts by 6.1% mIoU. Moreover, Seal demonstrates significant performance gains over existing methods across 20 different few-shot fine-tuning tasks on all eleven tested point cloud datasets.

PaperPDFConference PDFCodeCode 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

The archive's official repositories (youquanl/segment-any-point-cloud, xiaoaoran/SynLiDAR) were not harvested; the 24 samples below come from 4 repositories the archive does not mark official.

Syntology 24 code samples harvested from 4 repositories linked to this paper: 18 ran (of which 3 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 24 samples from 4 repositories, 18 ran (12 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 18 samples that ran has no recorded date.

youquanl/segment-any-point-cloud officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
xiaoaoran/SynLiDAR officialmentioned in paperMITSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

24 samples harvested: 18 ran (of which 3 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 6 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
12ran
6unverified

Licence: 6 of the 24 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 2 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.

subake/DAPS3D found in paper text by Syntology 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Bottleneck in 98 papers train/tasks/semantic/modules/ddrnet_23_slim_salsa_da.py ran · metamorphic tier: deterministic MIT (permissive) · ab585f4a45f6186a · report fixture: returned Bottleneck · level recorded 2026-09-22
DAPPM train/tasks/semantic/modules/ddrnet_23_slim_salsa_da.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 98542be0286d7f06 · report fixture: returned DAPPM · level recorded 2026-09-22
segmenthead train/tasks/semantic/modules/ddrnet_23_slim_salsa_da.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 093af22c7f46b460 · report fixture: returned segmenthead · level recorded 2026-09-22
DualResNet train/tasks/semantic/modules/ddrnet_23_slim_salsa_da.py unverified MIT (permissive) · b635e36051ab5ddb · report
TransformerStage train/tasks/semantic/modules/ddrnet_23_slim_salsa_da.py unverified MIT (permissive) · 7c9b14c925230f96 · report
valeoai/SLidR found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VisionTransformer in 53 papers model/modules/dino/vision_transformer.py ran fingerprinted licence not identified · pointer only · 684c765a98595395 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
microsoft/X-Decoder found in paper text by Syntology 4 samples, 4 ran (1 instrument-failed) · 0 unverified
build_decoder in 18 papers modeling/body/decoder/build.py ran Apache-2.0 (permissive) · e3b73f26b6efd55f · report fixture: returned MinimalDecoder · level recorded 2026-09-26
filter_images_with_only_crowd_annotations in 10 papers datasets/build.py ran · our draft was wrong Apache-2.0 (permissive) · a21a61e41d986b6a · report fixture: signature dataset_dicts:list/1/dict, dataset_names:list/1/str · returned list · level recorded 2026-09-25
register_decoder modeling/body/decoder/registry.py ran Apache-2.0 (permissive) · e3c3001fcab78f5c · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-26
register_norm_module in 5 papers utils/model.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e4f6733fa1ab1999 · report fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-24
IDEA-Research/OpenSeeD found in paper text by Syntology 14 samples, 10 ran (5 instrument-failed) · 4 unverified
batch_dice_loss in 60 papers openseed/modules/matcher.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · bc2cb481a75c370d · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float · returned Tensor · level recorded 2026-09-25
bbox_postprocess openseed/modules/postprocessing.py ran Apache-2.0 (permissive) · d3d81dca00185824 · report fixture: signature result:Tensor/2/float, input_size:tuple/1/int, img_size:tuple/1/int, output_height:int/0/int, output_width:int/0/int · returned Tensor · level recorded 2026-09-26
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
openseed/modules/criterion.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 89f75e54ff128be0 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
generate_regular_grid_point_coords openseed/modules/point_features.py ran Apache-2.0 (permissive) · 42ab1750d0229462 · report fixture: signature R:int/0/int, side_size:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
is_model in 24 papers openseed/architectures/registry.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 86c6e09f9f6f6637 · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-24
point_sample in 12 papers openseed/modules/point_features.py ran · our draft was wrong Apache-2.0 (permissive) · 39e4af93b70bcddf · report fixture: signature input:Tensor/4/float, point_coords:Tensor/3/float · returned Tensor · level recorded 2026-09-24
register_model in 68 papers openseed/architectures/registry.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · be2fbb8bf98a15f7 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
sem_seg_postprocess in 5 papers openseed/modules/postprocessing.py ran Apache-2.0 (permissive) · 0e8074c3542f9ab5 · report fixture: signature result:Tensor/3/float, img_size:tuple/1/int, output_height:int/0/int, output_width:int/0/int · returned Tensor · level recorded 2026-09-26
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
openseed/modules/criterion.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d0c61e8dba511aa3 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
openseed/modules/criterion.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
batch_sigmoid_ce_loss in 48 papers openseed/modules/matcher.py unverified Apache-2.0 (permissive) · 1edd24985036b0bf · report
build_model in 469 papers openseed/architectures/build.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · c67e4671ab9094aa · report
model_entrypoints openseed/architectures/registry.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 0c3902b80e9968b5 · report
multi_head_attention_forward in 73 papers openseed/modules/attention.py unverified Apache-2.0 (permissive) · 22a94fc69aed9aca · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Seal (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Seal (graph method: Seal). 5 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. DualResNet entry · level 0 · unverified · b635e36051ab5ddb
  2. Bottleneck model · level 1 · ran · ab585f4a45f6186a
  3. DAPPM model · level 1 · ran · 98542be0286d7f06
  4. TransformerStage model · level 0 · unverified · 7c9b14c925230f96
  5. segmenthead model · level 1 · ran · 093af22c7f46b460

harvested Assembly for Seal (graph method: Seal). 9 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. VisionTransformer entry · level 1 · ran · 684c765a98595395
  2. Block model · level 1 · ran · 65e124fb59929e7b
  3. PatchEmbed model · level 1 · ran · 9187f42531072c00
  4. trunc_normal_ helper · level 1 · ran; the contract check could not run · 915b71e73a54fc97
  5. Attention model · level 1 · ran · 3806102629027da3
  6. DropPath model · level 1 · ran · ad5f80b54573c0e0
  7. Mlp model · level 1 · ran · a1715055832f71fd
  8. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  9. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 32d549c7c63738c0

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="2306.09347") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Representation LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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