Papers › UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

15 Aug 2023ICCV 2023 1arXiv:2308.07732archive 2025-07-28

Haiyang Wang, Hao Tang, Shaoshuai Shi, Aoxue Li, Zhenguo Li, Bernt Schiele, LiWei Wang

Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems. However, current 3D perception research follows a modality-specific paradigm, leading to additional computation overheads and inefficient collaboration between different sensor data. In this paper, we present an efficient multi-modal backbone for outdoor 3D perception named UniTR, which processes a variety of modalities with unified modeling and shared parameters. Unlike previous works, UniTR introduces a modality-agnostic transformer encoder to handle these view-discrepant sensor data for parallel modal-wise representation learning and automatic cross-modal interaction without additional fusion steps. More importantly, to make full use of these complementary sensor types, we present a novel multi-modal integration strategy by both considering semantic-abundant 2D perspective and geometry-aware 3D sparse neighborhood relations. UniTR is also a fundamentally task-agnostic backbone that naturally supports different 3D perception tasks. It sets a new state-of-the-art performance on the nuScenes benchmark, achieving +1.1 NDS higher for 3D object detection and +12.0 higher mIoU for BEV map segmentation with lower inference latency. Code will be available at https://github.com/Haiyang-W/UniTR .

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 13 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 7 ran (6 with no instrument failure; 1 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

haiyang-w/unitr officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
haiyang-w/dsvt mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
haiyang-w/git mentioned on GitHubpytorchApache-2.0Syntology: 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.

Code Syntology ran Syntology

13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 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 last changed ; 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
9ran
3unverified

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 2 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”. “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.

haiyang-w/unitr official repository 4 samples, 3 ran (0 instrument-failed) · 1 unverified
get_points in 9 papers pcdet/models/model_utils/unitr_utils.py ran Apache-2.0 (permissive) · 9350ff1cc4c3a89f · report fixture: signature pc_range:list/1/int, sample_num:int/0/int, space_shape:list/1/int, coords:NoneType/0/? · returned Tensor · level recorded 2026-09-24
map_points pcdet/models/model_utils/unitr_utils.py ran Apache-2.0 (permissive) · 6b69ad0bb01a031c · report fixture: signature points:Tensor/3/float, lidar2image:Tensor/4/float, image_aug_matrix:Tensor/4/float, batch_size:int/0/int, image_shape:tuple/1/int · returned tuple · level recorded 2026-09-24
post_act_block_dense in 11 papers pcdet/models/backbones_3d/spconv_backbone_2d.py ran Apache-2.0 (permissive) · 0d095007c24b14c0 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, norm_fn:callable/0/? · returned Sequential · level recorded 2026-09-24
post_act_block in 31 papers pcdet/models/backbones_3d/spconv_backbone_2d.py unverified Apache-2.0 (permissive) · 016a882194742fe9 · report
haiyang-w/dsvt community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
cfg_from_yaml_file in 59 papers pcdet/config.py ran · our draft was wrong Apache-2.0 (permissive) · 44db2351bcc0bffe · report fixture: signature cfg_file:str/0/str, config:dict/0/? · returned EasyDict · level recorded 2026-09-25
compute_fg_mask in 36 papers pcdet/utils/loss_utils.py ran Apache-2.0 (permissive) · 65fe32ede00e7dcb · report fixture: signature gt_boxes2d:Tensor/3/float, shape:Size/1/int, downsample_factor:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-25
get_continous_inds pcdet/models/model_utils/dsvt_utils.py ran Apache-2.0 (permissive) · a6ede4e049fa3f68 · report fixture: signature setnum_per_win:Tensor/1/int · returned tuple · level recorded 2026-09-24
get_pooling_index pcdet/models/model_utils/dsvt_utils.py ran Apache-2.0 (permissive) · 161f7b84ad8cdafd · report fixture: signature coors:Tensor/2/int, sparse_shape:tuple/1/int, window_shape:tuple/1/int · returned tuple · level recorded 2026-09-24
get_window_coors pcdet/models/model_utils/dsvt_utils.py ran Apache-2.0 (permissive) · 629b2226cddc5153 · report fixture: signature coors:Tensor/2/int, sparse_shape:tuple/1/int, window_shape:tuple/1/int, do_shift:bool/0/bool, shift_list:NoneType/0/?, return_win_coors:bool/0/bool · returned tuple · level recorded 2026-09-24
merge_new_config in 59 papers pcdet/config.py ran Apache-2.0 (permissive) · 50e8e8cdfc5129f0 · report fixture: signature config:dict/0/?, new_config:dict/0/? · returned EasyDict · level recorded 2026-09-25
neg_loss_cornernet in 36 papers pcdet/utils/loss_utils.py ran Apache-2.0 (permissive) · 488b91d67a807558 · report fixture: signature pred:Tensor/4/float, gt:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
get_corner_loss_lidar in 51 papers pcdet/utils/loss_utils.py unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report
post_act_block in 31 papers pcdet/models/backbones_3d/spconv_backbone.py unverified Apache-2.0 (permissive) · 2b4e0558df870bf9 · 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 UniTR (graph method: UniTR). 10 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) · 1 unverified. The assembly has not been run end-to-end.

  1. Transformer entry · level 0 · unverified · 443cb18b71862421
  2. TransformerDecoder model · level 1 · ran · b41cfee48847d79e
  3. TransformerDecoderLayer model · level 1 · ran · 2cb413b2d6fa8f2e
  4. TransformerEncoder model · level 1 · ran · 10ec8fb6960c9e5e
  5. TransformerEncoderLayer model · level 1 · ran · 9f90c23222eb4bbf
  6. _get_clones helper · level 1 · ran · our draft was wrong · a8f1bbeb369e1829
  7. MultiHeadedAttention model · level 1 · ran · 671c67f4433ae3c1
  8. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  9. MLP model · level 1 · ran · 1630454d42cd8f1e
  10. attention helper · level 1 · ran · our draft was wrong · f93d42eb62cfe6e7

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="2308.07732") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Object DetectionAutonomous DrivingObject DetectionRepresentation Learningobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection nuScenes UniTR NDS 0.75 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mAAE 0.13 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mAOE 0.26 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mAP 0.71 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mASE 0.23 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mATE 0.24 #13 of 372 Archive leaderboard report
3D Object Detection nuScenes UniTR mAVE 0.24 #13 of 372 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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