# 3D Object Detection on V2X-Real Gaussian Pose Noise σ = 0.4 Source: [3D Object Detection on V2X-Real Gaussian Pose Noise σ = 0.4]() Collection index: [llms.txt]() Data updated: 2026-03-26T23:18:14.101Z Evaluation of 3D Object Detection performance on the V2X-Real dataset under specific Gaussian Pose Noise conditions (σ = 0.4). Metrics include class-specific Average Precision (AP) across IoU thresholds of 0.3, 0.5, and 0.7 for vehicle, pedestrian, and truck classes. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | 3D Object Detection | | Dataset (including any stated split) | V2X-Real Gaussian Pose Noise σ = 0.4 | | Metric | AP@0.3 (vehicle) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [AP@0.3 (vehicle)](): Higher is better; unit: PERCENT. - [AP@0.3 (pedestrian)](): Higher is better; unit: PERCENT. - [AP@0.3 (truck)](): Higher is better; unit: PERCENT. - [AP@0.3 (total)](): Higher is better; unit: PERCENT. - [AP@0.5 (vehicle)](): Higher is better; unit: PERCENT. - [AP@0.5 (pedestrian)](): Higher is better; unit: PERCENT. - [AP@0.5 (truck)](): Higher is better; unit: PERCENT. - [AP@0.5 (total)](): Higher is better; unit: PERCENT. - [AP@0.7 (vehicle)](): Higher is better; unit: PERCENT. - [AP@0.7 (pedestrian)](): Higher is better; unit: PERCENT. - [AP@0.7 (truck)](): Higher is better; unit: PERCENT. - [AP@0.7 (total)](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP@0.3 (vehicle) | Result date | Report paper | | --- | --- | --- | --- | | HyDRA w AG-PGO | 84.27 | Not recorded | 69c4bdae0636e5bf4afc76cb | | E2E Training | 83.9 | Not recorded | 69c4bdae0636e5bf4afc76cb | | HEAL | 83.76 | Not recorded | 69c4bdae0636e5bf4afc76cb | | HyDRA w CoAlign | 82.06 | Not recorded | 69c4bdae0636e5bf4afc76cb | | MPDA | 80.96 | Not recorded | 69c4bdae0636e5bf4afc76cb | | GenComm | 80.6 | Not recorded | 69c4bdae0636e5bf4afc76cb | | CodeFilling | 75.9 | Not recorded | 69c4bdae0636e5bf4afc76cb | | Late Fusion | 52.44 | Not recorded | 69c4bdae0636e5bf4afc76cb | ### HyDRA w AG-PGO AP@0.3 (vehicle): 84.27. Result ID: 69c5bd5a47f34ce924afd6e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### E2E Training AP@0.3 (vehicle): 83.9. Result ID: 69c5bd5a47f34ce924afd6e3. [Reporting paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### HEAL AP@0.3 (vehicle): 83.76. Result ID: 69c5bd5a47f34ce924afd6e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### HyDRA w CoAlign AP@0.3 (vehicle): 82.06. Result ID: 69c5bd5a47f34ce924afd6e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### MPDA AP@0.3 (vehicle): 80.96. Result ID: 69c5bd5a47f34ce924afd6e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### GenComm AP@0.3 (vehicle): 80.6. Result ID: 69c5bd5a47f34ce924afd6e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### CodeFilling AP@0.3 (vehicle): 75.9. Result ID: 69c5bd5a47f34ce924afd6e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. ### Late Fusion AP@0.3 (vehicle): 52.44. Result ID: 69c5bd5a47f34ce924afd6e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Gaussian Pose Noise (sigma)":"0.4","Architecture Heterogeneity Setting":"Ep+Hp+Xs+Xv"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.