Papers › RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

24 Jan 2023CVPR 2023 1arXiv:2301.10222archive 2025-07-28

Angelika Ando, Spyros Gidaris, Andrei Bursuc, Gilles Puy, Alexandre Boulch, Renaud Marlet

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with techniques which use other point cloud representations, achieve state-of-the-art results. Today, projection-based methods leverage 2D CNNs but recent advances in computer vision show that vision transformers (ViTs) have achieved state-of-the-art results in many image-based benchmarks. In this work, we question if projection-based methods for 3D semantic segmentation can benefit from these latest improvements on ViTs. We answer positively but only after combining them with three key ingredients: (a) ViTs are notoriously hard to train and require a lot of training data to learn powerful representations. By preserving the same backbone architecture as for RGB images, we can exploit the knowledge from long training on large image collections that are much cheaper to acquire and annotate than point clouds. We reach our best results with pre-trained ViTs on large image datasets. (b) We compensate ViTs' lack of inductive bias by substituting a tailored convolutional stem for the classical linear embedding layer. (c) We refine pixel-wise predictions with a convolutional decoder and a skip connection from the convolutional stem to combine low-level but fine-grained features of the the convolutional stem with the high-level but coarse predictions of the ViT encoder. With these ingredients, we show that our method, called RangeViT, outperforms existing projection-based methods on nuScenes and SemanticKITTI. The code is available at https://github.com/valeoai/rangevit.

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

Syntology 33 code samples: 32 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 33: 23 ran (of which 12 constructed an object rather than computing a result; 17 with no instrument failure: 4 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 32 samples from 1 repository, 22 ran (16 with no instrument failure; 6 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

valeoai/rangevit officialmentioned in papermentioned on GitHubpytorchSyntology: 32 samples, 22 ran (6 instrument-failed) · 10 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

33 samples harvested: 23 ran (of which 12 constructed an object rather than computing a result; 17 with no instrument failure: 4 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 10 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
1ran · violated contract
2ran · our draft was wrong
4ran; the contract check could not run
12ran
10unverified

Licence: 1 of the 33 samples is 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 valeoai/rangevit. 1 sample is listed last, in a group without a repository. “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 8 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.

valeoai/rangevit official repository 32 samples, 22 ran (6 instrument-failed) · 10 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/rangevit.py ran Apache-2.0 (permissive) · cec164e8a2ce78c9 · report fixture: returned Attention · 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/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a95957a1d20487a9 · report fixture: returned Block · level recorded 2026-09-22
ConvStem models/rangevit.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · ac1773d923b8d9e2 · report fixture: returned ConvStem · level recorded 2026-09-22
DecoderLinear models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · fe06d8e8349ec069 · report fixture: returned DecoderLinear · level recorded 2026-09-22
DecoderUpConv models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7a18eaf8e774211d · report fixture: returned DecoderUpConv · level recorded 2026-09-22
FeedForward in 198 papers models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 604e2495db9675ea · report fixture: returned FeedForward · level recorded 2026-09-22
PatchEmbedding in 25 papers models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 84bdbfecb1b19ac6 · report fixture: returned PatchEmbedding · level recorded 2026-09-22
RangeViT_KPConv models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e5e57595ef10210b · report fixture: returned RangeViT_KPConv · level recorded 2026-09-22
RangeViT_noKPConv models/rangevit.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · a3e4c0d909ed54df · report fixture: returned RangeViT_noKPConv · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/rangevit.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 4db77fb9e204e56b · report fixture: returned ResBlock · level recorded 2026-09-22
ResContextBlock models/rangevit.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 90645354e817adc7 · report fixture: returned ResContextBlock · level recorded 2026-09-22
UpConvBlock models/rangevit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 40208c8d6e460282 · report fixture: returned UpConvBlock · level recorded 2026-09-22
adapt_input_conv in 8 papers
census: 2 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
models/rangevit.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c58578dcfe39d5e3 · report fixture: signature in_chans:int/0/int, conv_weight:Tensor/4/float · returned Tensor · level recorded 2026-09-22
gather in 75 papers models/rangevit.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 06eb9b038422a6ef · report fixture: signature x:Tensor/3/float, idx:Tensor/2/int, method:int/0/int · returned Tensor · level recorded 2026-09-22
get_grid_size_1d models/rangevit.py ran · honoured contract Apache-2.0 (permissive) · d87e791164714d95 · report fixture: signature length:int/0/int, patch_size:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-22
get_grid_size_2d models/rangevit.py ran · honoured contract Apache-2.0 (permissive) · b7b03725c0cea60a · report fixture: signature H:int/0/int, W:int/0/int, patch_size:int/0/int, patch_stride:int/0/int · returned tuple · level recorded 2026-09-22
kernel_point_optimization_debug in 8 papers models/rangevit.py ran · our draft was wrong Apache-2.0 (permissive) · 92429fcd23170b41 · report fixture: signature radius:float/0/float, num_points:int/0/int, num_kernels:int/0/int, dimension:int/0/int, fixed:str/0/str, ratio:float/0/float, verbose:int/0/int · returned tuple · level recorded 2026-09-22
padding in 37 papers models/rangevit.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · faa633e27024c982 · report fixture: signature im:Tensor/4/float, patch_size:int/0/int, fill_value:int/0/int · returned Tensor · level recorded 2026-09-22
radius_gaussian in 11 papers models/rangevit.py ran · violated contract Apache-2.0 (permissive) · 42f2cd40ba483d3b · report fixture: signature sq_r:Tensor/3/float, sig:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
resize_pos_embed in 102 papers models/rangevit.py ran · our draft was wrong Apache-2.0 (permissive) · 039235a9d747b605 · report fixture: signature posemb:Tensor/3/float, grid_old_shape:tuple/1/int, grid_new_shape:tuple/1/int, num_extra_tokens:int/0/int · returned Tensor · level recorded 2026-09-22
spherical_Lloyd models/rangevit.py ran · honoured contract Apache-2.0 (permissive) · 4ab84fb06d2ccf79 · report fixture: signature radius:float/0/float, num_cells:int/0/int, dimension:int/0/int, fixed:str/0/str, approximation:str/0/str, approx_n:int/0/int, max_iter:int/0/int, momentum:float/0/float, verbose:int/0/int · returned ndarray · level recorded 2026-09-22
unpadding models/rangevit.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · f91d2b53f12127a0 · report fixture: signature y:Tensor/4/float, target_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
KPClassifier models/rangevit.py unverified Apache-2.0 (permissive) · cd6b811b76e85666 · report
KPConv models/rangevit.py unverified Apache-2.0 (permissive) · 8c5ddbf594c022e1 · report
RangeViT models/rangevit.py unverified Apache-2.0 (permissive) · 34a83804146235a8 · report
VisionTransformer in 53 papers models/rangevit.py unverified Apache-2.0 (permissive) · 6b3bd6eb6760b684 · report
create_decoder models/rangevit.py unverified Apache-2.0 (permissive) · 33d2c346ea1aa483 · report
create_rangevit models/rangevit.py unverified Apache-2.0 (permissive) · 6c8a129dc783ab5a · report
create_vit in 8 papers models/rangevit.py unverified Apache-2.0 (permissive) · 2be1b57c31497f10 · report
dist_barrier models/rangevit.py unverified Apache-2.0 (permissive) · 4543b408ae704bc3 · report
init_weights in 109 papers models/rangevit.py unverified Apache-2.0 (permissive) · 3f463ff854258680 · report
load_kernels models/rangevit.py unverified Apache-2.0 (permissive) · a39742896238e1ff · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
create_3D_rotations in 5 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · c545a5b0a698e295 · report fixture: signature axis:ndarray/2/float, angle:ndarray/1/float · returned ndarray · level recorded 2026-09-22

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 RangeViT (graph method: RangeViT). 38 bricks; individually on a fixture: 28 ran (of which 13 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 1 violated, 16 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. RangeViT entry · level 0 · unverified · 34a83804146235a8
  2. adapt_input_conv helper · level 1 · ran; the contract check could not run (RAISES) · c58578dcfe39d5e3
  3. count_parameters helper · level 1 · ran · honoured contract · f6b944f50d3f15ae
  4. create_rangevit helper · level 0 · unverified · 6c8a129dc783ab5a
  5. resize_pos_embed helper · level 1 · ran · our draft was wrong · 039235a9d747b605
  6. KPClassifier model · level 0 · unverified · cd6b811b76e85666
  7. RangeViT_KPConv model · level 1 · ran · e5e57595ef10210b
  8. RangeViT_noKPConv helper · level 1 · ran · a3e4c0d909ed54df
  9. create_decoder helper · level 0 · unverified · 33d2c346ea1aa483
  10. create_vit helper · level 0 · unverified · 2be1b57c31497f10
  11. KPConv helper · level 0 · unverified · 8c5ddbf594c022e1
  12. padding helper · level 1 · ran; the contract check could not run (RAISES) · faa633e27024c982
  13. unpadding helper · level 1 · ran; the contract check could not run (RAISES) · f91d2b53f12127a0
  14. DecoderLinear model · level 1 · ran · fe06d8e8349ec069
  15. DecoderUpConv model · level 1 · ran · 7a18eaf8e774211d
  16. VisionTransformer model · level 0 · unverified · 6b3bd6eb6760b684
  17. dist_barrier helper · level 0 · unverified · 4543b408ae704bc3
  18. gather helper · level 1 · ran; the contract check could not run (RAISES) · 06eb9b038422a6ef
  19. is_main_process helper · level 1 · ran · e4d71e90ee09ce61
  20. load_kernels helper · level 0 · unverified · a39742896238e1ff
  21. radius_gaussian helper · level 1 · ran · violated contract · 42f2cd40ba483d3b
  22. get_grid_size_2d helper · level 1 · ran · honoured contract · b7b03725c0cea60a
  23. init_weights helper · level 0 · unverified · 3f463ff854258680
  24. UpConvBlock helper · level 1 · ran · 40208c8d6e460282
  25. Block helper · level 1 · ran · a95957a1d20487a9
  26. ConvStem helper · level 1 · ran · ac1773d923b8d9e2
  27. PatchEmbedding helper · level 1 · ran · 84bdbfecb1b19ac6
  28. is_dist_avail_and_initialized helper · level 1 · ran · 5f205488cb7b9004
  29. get_rank helper · level 1 · ran · 41ff89724cf234e1
  30. create_3D_rotations helper · level 1 · ran · honoured contract · c545a5b0a698e295
  31. kernel_point_optimization_debug helper · level 1 · ran · our draft was wrong · 92429fcd23170b41
  32. spherical_Lloyd helper · level 1 · ran · honoured contract · 4ab84fb06d2ccf79
  33. get_grid_size_1d helper · level 1 · ran · honoured contract · d87e791164714d95
  34. Attention helper · level 1 · ran · cec164e8a2ce78c9
  35. FeedForward helper · level 1 · ran · 604e2495db9675ea
  36. LayerScale helper · level 1 · ran · 53f7f1cd1032ac80
  37. ResBlock helper · level 1 · ran · 4db77fb9e204e56b
  38. ResContextBlock helper · level 1 · ran · 90645354e817adc7

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="2301.10222") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Semantic SegmentationAutonomous DrivingInductive BiasSemantic Segmentation

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