Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804922> ?p ?o ?g. }
- W4385804922 abstract "To achieve autonomous driving, developing 3D detection fusion methods, which aim to fuse the camera and LiDAR information, has draw great research interest in recent years. As a common practice, people rely on large-scale datasets to fairly compare the performance of different methods. While these datasets have been carefully cleaned to ideally minimize any potential noise, we observe that they cannot truly reflect the data seen on a real autonomous vehicle, whose data tends to be noisy due to various reasons. This hinders the ability to simply estimate the robust performance under realistic noisy settings. To this end, we collect a series of real-world cases with noisy data distribution, and systematically formulate a robustness benchmark toolkit. It can simulate these cases on any clean dataset, which has the camera and LiDAR input modality. We showcase the effectiveness of our toolkit by establishing two novel robustness benchmarks on widely-adopted datasets, nuScenes and Waymo, then holistically evaluate the state-of-the-art fusion methods. We discover that: i) most fusion methods, when solely developed on these data, tend to fail inevitably when there is a disruption to the LiDAR input; ii) the improvement of the camera input is significantly inferior to the LiDAR one. We publish the robust fusion dataset, benchmark, detailed documents and instructions on https://anonymous-benchmark.github.io/robust-benchmark-website." @default.
- W4385804922 created "2023-08-15" @default.
- W4385804922 creator A5004709181 @default.
- W4385804922 creator A5007006789 @default.
- W4385804922 creator A5013652689 @default.
- W4385804922 creator A5016399094 @default.
- W4385804922 creator A5019884153 @default.
- W4385804922 creator A5023446490 @default.
- W4385804922 creator A5040040696 @default.
- W4385804922 creator A5047878798 @default.
- W4385804922 creator A5081233515 @default.
- W4385804922 creator A5089296571 @default.
- W4385804922 date "2023-06-01" @default.
- W4385804922 modified "2023-10-16" @default.
- W4385804922 title "Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection" @default.
- W4385804922 cites W1512698229 @default.
- W4385804922 cites W2194775991 @default.
- W4385804922 cites W2555618208 @default.
- W4385804922 cites W2565639579 @default.
- W4385804922 cites W2601564443 @default.
- W4385804922 cites W2897529137 @default.
- W4385804922 cites W2951517617 @default.
- W4385804922 cites W2963323244 @default.
- W4385804922 cites W2963400571 @default.
- W4385804922 cites W2963727135 @default.
- W4385804922 cites W2964062501 @default.
- W4385804922 cites W2967324759 @default.
- W4385804922 cites W2968296999 @default.
- W4385804922 cites W2997162428 @default.
- W4385804922 cites W3034314779 @default.
- W4385804922 cites W3034543232 @default.
- W4385804922 cites W3035172746 @default.
- W4385804922 cites W3035346742 @default.
- W4385804922 cites W3035461736 @default.
- W4385804922 cites W3118479569 @default.
- W4385804922 cites W3119884503 @default.
- W4385804922 cites W3127743092 @default.
- W4385804922 cites W3130463448 @default.
- W4385804922 cites W3167095230 @default.
- W4385804922 cites W3167732492 @default.
- W4385804922 cites W3170030651 @default.
- W4385804922 cites W3172261075 @default.
- W4385804922 cites W3173668541 @default.
- W4385804922 cites W3176319743 @default.
- W4385804922 cites W3176821088 @default.
- W4385804922 cites W3187011621 @default.
- W4385804922 cites W3193939309 @default.
- W4385804922 cites W3204439495 @default.
- W4385804922 cites W3209459195 @default.
- W4385804922 cites W3209639308 @default.
- W4385804922 cites W4214558638 @default.
- W4385804922 cites W4225986494 @default.
- W4385804922 cites W4312543476 @default.
- W4385804922 cites W4312564076 @default.
- W4385804922 cites W4312707458 @default.
- W4385804922 cites W4312894406 @default.
- W4385804922 doi "https://doi.org/10.1109/cvprw59228.2023.00321" @default.
- W4385804922 hasPublicationYear "2023" @default.
- W4385804922 type Work @default.
- W4385804922 citedByCount "1" @default.
- W4385804922 countsByYear W43858049222023 @default.
- W4385804922 crossrefType "proceedings-article" @default.
- W4385804922 hasAuthorship W4385804922A5004709181 @default.
- W4385804922 hasAuthorship W4385804922A5007006789 @default.
- W4385804922 hasAuthorship W4385804922A5013652689 @default.
- W4385804922 hasAuthorship W4385804922A5016399094 @default.
- W4385804922 hasAuthorship W4385804922A5019884153 @default.
- W4385804922 hasAuthorship W4385804922A5023446490 @default.
- W4385804922 hasAuthorship W4385804922A5040040696 @default.
- W4385804922 hasAuthorship W4385804922A5047878798 @default.
- W4385804922 hasAuthorship W4385804922A5081233515 @default.
- W4385804922 hasAuthorship W4385804922A5089296571 @default.
- W4385804922 hasBestOaLocation W43858049222 @default.
- W4385804922 hasConcept C104317684 @default.
- W4385804922 hasConcept C119599485 @default.
- W4385804922 hasConcept C124101348 @default.
- W4385804922 hasConcept C127313418 @default.
- W4385804922 hasConcept C127413603 @default.
- W4385804922 hasConcept C13280743 @default.
- W4385804922 hasConcept C141353440 @default.
- W4385804922 hasConcept C144133560 @default.
- W4385804922 hasConcept C153180895 @default.
- W4385804922 hasConcept C154945302 @default.
- W4385804922 hasConcept C162853370 @default.
- W4385804922 hasConcept C185592680 @default.
- W4385804922 hasConcept C185798385 @default.
- W4385804922 hasConcept C205649164 @default.
- W4385804922 hasConcept C2776151529 @default.
- W4385804922 hasConcept C31972630 @default.
- W4385804922 hasConcept C33954974 @default.
- W4385804922 hasConcept C41008148 @default.
- W4385804922 hasConcept C51399673 @default.
- W4385804922 hasConcept C55493867 @default.
- W4385804922 hasConcept C62649853 @default.
- W4385804922 hasConcept C63479239 @default.
- W4385804922 hasConcept C86251818 @default.
- W4385804922 hasConceptScore W4385804922C104317684 @default.
- W4385804922 hasConceptScore W4385804922C119599485 @default.
- W4385804922 hasConceptScore W4385804922C124101348 @default.
- W4385804922 hasConceptScore W4385804922C127313418 @default.