Papers › Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D...

Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

5 Mar 2019arXiv:1903.01864archive 2025-07-28

Zhixin Wang, Kui Jia

In this work, we propose a novel method termed Frustum ConvNet (F-ConvNet) for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustum-level feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustum-level features and supports an end-to-end and continuous estimation of oriented boxes in the 3D space. We also propose component variants of F-ConvNet, including an FCN variant that extracts multi-resolution frustum features, and a refined use of F-ConvNet over a reduced 3D space. Careful ablation studies verify the efficacy of these component variants. F-ConvNet assumes no prior knowledge of the working 3D environment and is thus dataset-agnostic. We present experiments on both the indoor SUN-RGBD and outdoor KITTI datasets. F-ConvNet outperforms all existing methods on SUN-RGBD, and at the time of submission it outperforms all published works on the KITTI benchmark. Code has been made available at: {https://github.com/zhixinwang/frustum-convnet.}

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 16 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 15 ran (14 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.

zhixinwang/frustum-convnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 15 ran (1 instrument-failed) · 1 unverified report
carterprice2/Deep_Learning_project mentioned on GitHubSyntology: 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

16 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran; the contract check could not run
14ran
1unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 zhixinwang/frustum-convnet. “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.

zhixinwang/frustum-convnet official repository 16 samples, 15 ran (1 instrument-failed) · 1 unverified
in_hull in 13 papers datasets/data_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) here; the stored copy is pointer only · aab935d4b7b55c2c · report fixture: signature p:ndarray/2/float, hull:Delaunay/0/? · returned ndarray · level recorded, date not recorded
Conv1d in 12 papers models/common.py ran MIT (permissive) · df9e498714c411f2 · report fixture: signature i_c:int/0/int, o_c:int/0/int, k:int/0/int, s:int/0/int, p:int/0/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-25
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
models/common.py ran MIT (permissive) · ce58b42def83bfb4 · report fixture: signature i_c:int/0/int, o_c:int/0/int, k:int/0/int, s:int/0/int, p:int/0/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-25
Conv3d models/common.py ran MIT (permissive) · e0f1f2d3ccac5f2e · report fixture: signature i_c:int/0/int, o_c:int/0/int, k:int/0/int, s:int/0/int, p:int/0/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-25
adjust_coord_for_view datasets/check_utils.py ran fingerprinted MIT (permissive) · 3b86dc1730e8d1c1 · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-25
center_decode models/box_transform.py ran fingerprinted MIT (permissive) · f47e771020b20fef · report fixture: signature ex:Tensor/2/float, offset:Tensor/2/float · returned Tensor · level recorded 2026-09-25
collate_fn in 500 papers datasets/provider_sample.py ran fingerprinted MIT (permissive) · 0c5c08f1db6108da · report fixture: signature batch:list/1/tuple · returned list · level recorded 2026-09-25
compute_alpha in 26 papers datasets/provider_sample.py ran MIT (permissive) · 8d0c2b6ba5dcbf2d · report fixture: signature x:ndarray/1/float, z:ndarray/1/float, ry:ndarray/1/float · returned ndarray · level recorded 2026-09-25
extract_pc_in_box3d in 7 papers datasets/data_utils.py ran fingerprinted MIT (permissive) · 4b69faf22a81a1e4 · report fixture: signature pc:ndarray/2/float, box3d:ndarray/2/float · returned ndarray · level recorded 2026-09-25
get_box3d_corners_helper models/model_util.py ran MIT (permissive) · 281f3748f309afc2 · report fixture: signature centers:Tensor/2/float, headings:Tensor/1/float, sizes:Tensor/2/float · returned Tensor · level recorded 2026-09-25
huber_loss in 34 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
models/model_util.py ran MIT (permissive) · f6eae958a22ae877 · report fixture: signature error:Tensor/2/float, delta:float/0/float, weight:Tensor/2/float · returned Tensor · level recorded 2026-09-25
rotate_pc_along_y datasets/data_utils.py ran fingerprinted MIT (permissive) · fda77318c74af228 · report fixture: signature pc:ndarray/2/float, rot_angle:float/0/float · returned ndarray · level recorded 2026-09-25
size_decode models/box_transform.py ran MIT (permissive) · 9989d7e45fda73c4 · report fixture: signature offset:Tensor/3/float, class_mean_size:Tensor/2/float, size_class_label:Tensor/1/int · returned Tensor · level recorded 2026-09-25
size_encode models/box_transform.py ran fingerprinted MIT (permissive) · 53a9950814898b9c · report fixture: signature gt:Tensor/2/float, class_mean_size:Tensor/2/float, size_class_label:int/0/int · returned Tensor · level recorded 2026-09-25
smooth_l1_loss in 28 papers models/model_util.py ran fingerprinted MIT (permissive) · ce156beb68c9daa3 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, sigma:float/0/float, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-25
load_cfg in 17 papers configs/config.py unverified MIT (permissive) · a124059a5c42fe93 · report

Tasks

3D Object DetectionObject DetectionRegion Proposalobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection KITTI Cars Easy F-ConvNet AP 85.88% #17 of 26 Archive leaderboard report
3D Object Detection KITTI Cars Hard F-ConvNet AP 68.08% #17 of 25 Archive leaderboard report
3D Object Detection KITTI Cyclists Easy F-ConvNet AP 79.58% #3 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Hard F-ConvNets AP 57.03% #5 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Moderate F-ConvNet AP 64.68% #4 of 13 Archive leaderboard report
3D Object Detection KITTI Pedestrians Easy F-ConvNet AP 52.37% #4 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Hard F-ConvNet AP 41.49% #4 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Moderate F-ConvNet AP 43.38% #6 of 12 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.

Methods

ConvolutionFCNMax Pooling

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