Papers › EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

21 Dec 2021arXiv:2112.11088archive 2025-07-28

Zhe Liu, Tengteng Huang, Bingling Li, Xiwu Chen, Xi Wang, Xiang Bai

Recently, fusing the LiDAR point cloud and camera image to improve the performance and robustness of 3D object detection has received more and more attention, as these two modalities naturally possess strong complementarity. In this paper, we propose EPNet++ for multi-modal 3D object detection by introducing a novel Cascade Bi-directional Fusion (CB-Fusion) module and a Multi-Modal Consistency (MC) loss. More concretely, the proposed CB-Fusion module enhances point features with plentiful semantic information absorbed from the image features in a cascade bi-directional interaction fusion manner, leading to more powerful and discriminative feature representations. The MC loss explicitly guarantees the consistency between predicted scores from two modalities to obtain more comprehensive and reliable confidence scores. The experimental results on the KITTI, JRDB and SUN-RGBD datasets demonstrate the superiority of EPNet++ over the state-of-the-art methods. Besides, we emphasize a critical but easily overlooked problem, which is to explore the performance and robustness of a 3D detector in a sparser scene. Extensive experiments present that EPNet++ outperforms the existing SOTA methods with remarkable margins in highly sparse point cloud cases, which might be an available direction to reduce the expensive cost of LiDAR sensors. Code is available at: https://github.com/happinesslz/EPNetV2.

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 17 code samples: 15 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 17: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 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, 11 ran (8 with no instrument failure; 3 where Syntology's instrument failed); 2 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 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 13 samples that ran has no recorded date.

happinesslz/epnetv2 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 11 ran (3 instrument-failed) · 4 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

17 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 4 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 · our draft was wrong
1ran; the contract check could not run
8ran
4unverified

Licence: 5 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 happinesslz/epnetv2. 2 samples are 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”. “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.

happinesslz/epnetv2 official repository 15 samples, 11 ran (3 instrument-failed) · 4 unverified
Feature_Gather lib/net/point_rcnn.py ran MIT (permissive) · f42100530caf4875 · report fixture: signature feature_map:Tensor/4/float, xy:Tensor/3/float · returned Tensor · level recorded 2026-09-25
Feature_Gather lib/net/rcnn_net.py ran MIT (permissive) · 4c4d06c304942b4b · report fixture: signature feature_map:Tensor/4/float, xy:Tensor/3/float · returned Tensor · level recorded 2026-09-24
conv1x1 in 691 papers lib/net/pointnet2_msg.py ran · our draft was wrong MIT (permissive) · cad594317b0f657a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-24
conv3x3 in 1,376 papers lib/net/pointnet2_msg.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
flatten_binary_logits lib/net/lovasz_loss.py ran MIT (permissive) · 6467b6d3f3fca80f · report fixture: signature logits:Tensor/2/float, labels:Tensor/2/int, ignore_index:int/0/int · returned tuple · level recorded 2026-09-24
flatten_probs lib/net/lovasz_loss.py ran MIT (permissive) · e028f43bbba9e8c0 · report fixture: signature probs:Tensor/4/float, labels:Tensor/3/int, ignore_index:NoneType/0/? · returned tuple · level recorded 2026-09-24
lovasz_grad in 42 papers lib/net/lovasz_loss.py ran fingerprinted MIT (permissive) · 87e40f2872a4cfa5 · report fixture: signature gt_sorted:Tensor/1/int · returned Tensor · level recorded 2026-09-24
reduce_loss in 75 papers lib/net/seg_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · b2b9a1966482ef96 · report fixture: signature loss:Tensor/1/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
sigmoid_func lib/datasets/kitti_rcnn_dataset.py ran fingerprinted MIT (permissive) · d4ce156fa1747c75 · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-24
weight_reduce_loss in 61 papers lib/net/seg_utils.py ran MIT (permissive) here; the stored copy is pointer only · 9a78b68ccf3be3bb · report fixture: signature loss:Tensor/2/float, weight:Tensor/2/float, reduction:str/0/str, avg_factor:float/0/float · returned Tensor · level recorded 2026-09-26
weighted_loss in 53 papers lib/net/seg_utils.py ran MIT (permissive) · 1cba2eaeeb7e3cad · report fixture: signature loss_func:callable/0/? · returned function · level recorded 2026-09-24
binary_cross_entropy in 19 papers lib/net/cross_entropy_loss.py unverified MIT (permissive) · c2c6075384f7da61 · report
interpolate_img_by_xy lib/datasets/kitti_rcnn_dataset.py unverified MIT (permissive) · 675132277ed16adf · report
mask_cross_entropy in 5 papers lib/net/cross_entropy_loss.py unverified MIT (permissive) · 9dd6cc0f7220b833 · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are 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_logger in 172 papers repository not located ran · our draft was wrong licence of this copy not recorded · bae007593bd3dfd1 · report fixture: signature log_file:str/0/str · returned Logger · level recorded 2026-09-22
create_logger in 172 papers repository not located ran · our draft was wrong licence of this copy not recorded · c349bc6f8ed16220 · report fixture: signature log_file:str/0/str · returned Logger · level recorded 2026-09-22

Tasks

3D Object DetectionObject Detectionobject-detection

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