Papers › FUTR3D: A Unified Sensor Fusion Framework for 3D Detection

FUTR3D: A Unified Sensor Fusion Framework for 3D Detection

20 Mar 2022arXiv:2203.10642archive 2025-07-28

Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, Hang Zhao

Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics. Existing multi-modal 3D detection models usually involve customized designs depending on the sensor combinations or setups. In this work, we propose the first unified end-to-end sensor fusion framework for 3D detection, named FUTR3D, which can be used in (almost) any sensor configuration. FUTR3D employs a query-based Modality-Agnostic Feature Sampler (MAFS), together with a transformer decoder with a set-to-set loss for 3D detection, thus avoiding using late fusion heuristics and post-processing tricks. We validate the effectiveness of our framework on various combinations of cameras, low-resolution LiDARs, high-resolution LiDARs, and Radars. On NuScenes dataset, FUTR3D achieves better performance over specifically designed methods across different sensor combinations. Moreover, FUTR3D achieves great flexibility with different sensor configurations and enables low-cost autonomous driving. For example, only using a 4-beam LiDAR with cameras, FUTR3D (58.0 mAP) achieves on par performance with state-of-the-art 3D detection model CenterPoint (56.6 mAP) using a 32-beam LiDAR.

PaperPDFCodeCode Syntology ran

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 19 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 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: community (archive-listed): 19 samples from 2 repositories, 17 ran (10 with no instrument failure; 7 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.

tsinghua-mars-lab/futr3d mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 7 ran (3 instrument-failed) · 2 unverified report
xiaohao-xu/unified-pretrain-ad mentioned on GitHubpytorchMITSyntology: 10 samples, 10 ran (4 instrument-failed) · 0 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

19 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 2 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.

5ran · our draft was wrong
2ran; the contract check could not run
10ran
2unverified

Licence: 4 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 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. 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.

tsinghua-mars-lab/futr3d community (archive-listed) 9 samples, 7 ran (3 instrument-failed) · 2 unverified
conv1x1 in 691 papers plugin/futr3d/models/backbone/vovnet.py ran Apache-2.0 (permissive) · c637c42a302bb63c · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, module_name:str/0/str, postfix:str/0/str, stride:int/0/int, groups:int/0/int, kernel_size:int/0/int, padding:int/0/int · returned list · level recorded 2026-09-24
conv3x3 in 1,376 papers plugin/futr3d/models/backbone/vovnet.py ran Apache-2.0 (permissive) · 303f4d3695ad18f1 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, module_name:str/0/str, postfix:str/0/str, stride:int/0/int, groups:int/0/int, kernel_size:int/0/int, padding:int/0/int · returned list · level recorded 2026-09-24
denormalize_bbox in 15 papers plugin/futr3d/core/bbox/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b8cdf4cad83ce917 · report fixture: signature normalized_bboxes:Tensor/2/float, pc_range:NoneType/0/? · returned Tensor · level recorded 2026-09-24
feature_sampling plugin/futr3d/models/utils/futr3d_attention.py ran Apache-2.0 (permissive) · ac73da5ed8412961 · report fixture: signature mlvl_feats:list/1/Tensor, reference_points:Tensor/3/float, pc_range:list/1/float, img_metas:list/1/dict · returned tuple · level recorded 2026-09-24
get_paddings_indicator plugin/futr3d/models/backbone/radar_encoder.py ran Apache-2.0 (permissive) · 5e13611ee307d69a · report fixture: signature actual_num:Tensor/1/int, max_num:int/0/int, axis:int/0/int · returned Tensor · level recorded 2026-09-24
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
plugin/futr3d/models/utils/futr3d_attention.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f3855be53d36327d · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-25
normalize_bbox in 23 papers plugin/futr3d/core/bbox/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 8800486c70b30b88 · report fixture: signature bboxes:Tensor/2/float, pc_range:NoneType/0/? · returned Tensor · level recorded 2026-09-24
dw_conv3x3 in 9 papers plugin/futr3d/models/backbone/vovnet.py unverified Apache-2.0 (permissive) · 5ebf15e6940f6710 · report
reduce_LiDAR_beams plugin/futr3d/datasets/loading.py unverified Apache-2.0 (permissive) · d061ed2b287db1a4 · report
xiaohao-xu/unified-pretrain-ad community (archive-listed) 10 samples, 10 ran (4 instrument-failed) · 0 unverified
aligned_3d_nms in 5 papers mmdet3d/core/post_processing/box3d_nms.py ran MIT (permissive) · 0079ed3e99e4048d · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, classes:Tensor/1/int, thresh:float/0/float · returned Tensor · level recorded 2026-09-25
box_camera_to_lidar in 10 papers mmdet3d/core/bbox/box_np_ops.py ran MIT (permissive) · 96c8084488bd023b · report fixture: signature data:ndarray/2/float, r_rect:ndarray/2/float, velo2cam:ndarray/2/float · returned ndarray · level recorded 2026-09-25
camera_to_lidar in 10 papers mmdet3d/core/bbox/box_np_ops.py ran MIT (permissive) · 9e22984820c39868 · report fixture: signature points:ndarray/2/float, r_rect:ndarray/2/float, velo2cam:ndarray/2/float · returned ndarray · level recorded 2026-09-25
circle_nms in 5 papers mmdet3d/core/post_processing/box3d_nms.py ran MIT (permissive) · a8007c7a213459b2 · report fixture: signature dets:ndarray/2/float, thresh:float/0/float, post_max_size:int/0/int · returned list · level recorded 2026-09-25
corners_nd in 9 papers mmdet3d/core/bbox/box_np_ops.py ran; the contract check could not run (RAISES) MIT (permissive) · 5b1dacd1f125c08f · report fixture: signature dims:ndarray/2/float, origin:float/0/float · returned ndarray · level recorded 2026-09-25
denormalize_bbox in 15 papers mmdet3d/core/bbox/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 38e90d12ef38fe79 · report fixture: signature normalized_bboxes:Tensor/2/float, pc_range:list/1/float · returned Tensor · level recorded 2026-09-24
draw_heatmap_gaussian mmdet3d/core/utils/gaussian.py ran MIT (permissive) · a7cde40ccc6422e2 · report fixture: signature heatmap:Tensor/2/float, center:Tensor/1/float, radius:int/0/int, k:int/0/int · returned Tensor · level recorded 2026-09-25
gaussian_2d in 11 papers mmdet3d/core/utils/gaussian.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · ea036153b550642a · report fixture: signature shape:list/1/int, sigma:float/0/float · returned ndarray · level recorded 2026-09-24
gaussian_radius in 25 papers mmdet3d/core/utils/gaussian.py ran MIT (permissive) · 73e8316be86a800d · report fixture: signature det_size:tuple/1/Tensor, min_overlap:float/0/float · returned Tensor · level recorded 2026-09-25
normalize_bbox in 23 papers mmdet3d/core/bbox/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e6ab81c2ff932920 · report fixture: signature bboxes:Tensor/2/float, pc_range:list/1/float · returned Tensor · level recorded 2026-09-24

Tasks

Autonomous DrivingDecoderSensor Fusion

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