Papers › V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

8 Aug 2023arXiv:2308.04409archive 2025-07-28

Yichao Shen, Zigang Geng, Yuhui Yuan, Yutong Lin, Ze Liu, Chunyu Wang, Han Hu, Nanning Zheng, Baining Guo

We introduce a highly performant 3D object detector for point clouds using the DETR framework. The prior attempts all end up with suboptimal results because they fail to learn accurate inductive biases from the limited scale of training data. In particular, the queries often attend to points that are far away from the target objects, violating the locality principle in object detection. To address the limitation, we introduce a novel 3D Vertex Relative Position Encoding (3DV-RPE) method which computes position encoding for each point based on its relative position to the 3D boxes predicted by the queries in each decoder layer, thus providing clear information to guide the model to focus on points near the objects, in accordance with the principle of locality. In addition, we systematically improve the pipeline from various aspects such as data normalization based on our understanding of the task. We show exceptional results on the challenging ScanNetV2 benchmark, achieving significant improvements over the previous 3DETR in AP₂₅/AP₅₀ from 65.0\%/47.0\% to 77.8\%/66.0\%, respectively. In addition, our method sets a new record on ScanNetV2 and SUN RGB-D datasets.Code will be released at http://github.com/yichaoshen-MS/V-DETR.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.04409")

Code

Syntology Ran 10 of 12 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yichaoshen-ms/v-detr officialmentioned in paperpytorchMIT 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

12 samples harvested; 10 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
7ran
2unverified

Licence: 0 of the 12 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 yichaoshen-ms/v-detr. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

adjust_learning_rate yichaoshen-ms/v-detr/engine.py official repository ran MIT (permissive) · 2908efab7e71b5a8 · report
build_optimizer yichaoshen-ms/v-detr/optimizer.py official repository ran MIT (permissive) · da4f8d084fea1b3e · report
compute_learning_rate yichaoshen-ms/v-detr/engine.py official repository ran MIT (permissive) · 38f2153fcc1523d8 · report
convert_corners_camera2lidar yichaoshen-ms/v-detr/models/vdetr_transformer.py official repository ran fingerprinted MIT (permissive) · c442c7a276779ddf · report
get_clones yichaoshen-ms/v-detr/models/helpers.py official repository ran · our draft was wrong MIT (permissive) · 891b8ebab395921f · report
inverse_sigmoid yichaoshen-ms/v-detr/models/vdetr_transformer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 83c03ceb1307c6c4 · report
read_plymesh yichaoshen-ms/v-detr/datasets/scannet.py official repository ran MIT (permissive) · 484cab6df3da608c · report
read_segmentation yichaoshen-ms/v-detr/datasets/scannet.py official repository ran MIT (permissive) · 395ce1c22ca13d08 · report
roty_batch_tensor yichaoshen-ms/v-detr/models/vdetr_transformer.py official repository ran fingerprinted MIT (permissive) · f99bc72a07da96e0 · report
sigmoid_focal_loss yichaoshen-ms/v-detr/criterion.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5c0711aada67957e · report
convert_unnorm2norm yichaoshen-ms/v-detr/models/model_vdetr.py official repository unverified MIT (permissive) · 47cc74bdb126783e · report
get_release_scans yichaoshen-ms/v-detr/scannet/download-scannet.py official repository unverified MIT (permissive) · 1d1b94d9af6bae68 · report

Tasks

3D Object DetectionDecoderObject Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection SUN-RGBD val V-DETR mAP@0.25 68.0 #4 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val V-DETR mAP@0.5 51.1 #4 of 32 Archive leaderboard report
3D Object Detection ScanNetV2 V-DETR mAP@0.25 77.8 #3 of 33 Archive leaderboard report
3D Object Detection ScanNetV2 V-DETR mAP@0.5 65.9 #3 of 33 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDetrDropoutFeedforward NetworkFocusLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerfail

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