Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320341405> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4320341405 abstract "Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth estimation. Previous works usually use a direct estimation method. However, in this paper we point out that the instance depth on the RGB image is non-intuitive. It is coupled by visual depth clues and instance attribute clues, making it hard to be directly learned in the network. Therefore, we propose to reformulate the instance depth to the combination of the instance visual surface depth (visual depth) and the instance attribute depth (attribute depth). The visual depth is related to objects' appearances and positions on the image. By contrast, the attribute depth relies on objects' inherent attributes, which are invariant to the object affine transformation on the image. Correspondingly, we decouple the 3D location uncertainty into visual depth uncertainty and attribute depth uncertainty. By combining different types of depths and associated uncertainties, we can obtain the final instance depth. Furthermore, data augmentation in monocular 3D detection is usually limited due to the physical nature, hindering the boost of performance. Based on the proposed instance depth disentanglement strategy, we can alleviate this problem. Evaluated on KITTI, our method achieves new state-of-the-art results, and extensive ablation studies validate the effectiveness of each component in our method. The codes are released at https://github.com/SPengLiang/DID-M3D." @default.
- W4320341405 created "2023-02-13" @default.
- W4320341405 creator A5005064985 @default.
- W4320341405 creator A5006219225 @default.
- W4320341405 creator A5016856595 @default.
- W4320341405 creator A5037942269 @default.
- W4320341405 creator A5058510872 @default.
- W4320341405 date "2022-07-18" @default.
- W4320341405 modified "2023-10-14" @default.
- W4320341405 title "DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection" @default.
- W4320341405 doi "https://doi.org/10.48550/arxiv.2207.08531" @default.
- W4320341405 hasPublicationYear "2022" @default.
- W4320341405 type Work @default.
- W4320341405 citedByCount "0" @default.
- W4320341405 crossrefType "posted-content" @default.
- W4320341405 hasAuthorship W4320341405A5005064985 @default.
- W4320341405 hasAuthorship W4320341405A5006219225 @default.
- W4320341405 hasAuthorship W4320341405A5016856595 @default.
- W4320341405 hasAuthorship W4320341405A5037942269 @default.
- W4320341405 hasAuthorship W4320341405A5058510872 @default.
- W4320341405 hasBestOaLocation W43203414051 @default.
- W4320341405 hasConcept C115961682 @default.
- W4320341405 hasConcept C141268832 @default.
- W4320341405 hasConcept C153180895 @default.
- W4320341405 hasConcept C154945302 @default.
- W4320341405 hasConcept C190470478 @default.
- W4320341405 hasConcept C202444582 @default.
- W4320341405 hasConcept C2781238097 @default.
- W4320341405 hasConcept C31972630 @default.
- W4320341405 hasConcept C33923547 @default.
- W4320341405 hasConcept C37914503 @default.
- W4320341405 hasConcept C41008148 @default.
- W4320341405 hasConcept C65909025 @default.
- W4320341405 hasConcept C82990744 @default.
- W4320341405 hasConcept C92757383 @default.
- W4320341405 hasConceptScore W4320341405C115961682 @default.
- W4320341405 hasConceptScore W4320341405C141268832 @default.
- W4320341405 hasConceptScore W4320341405C153180895 @default.
- W4320341405 hasConceptScore W4320341405C154945302 @default.
- W4320341405 hasConceptScore W4320341405C190470478 @default.
- W4320341405 hasConceptScore W4320341405C202444582 @default.
- W4320341405 hasConceptScore W4320341405C2781238097 @default.
- W4320341405 hasConceptScore W4320341405C31972630 @default.
- W4320341405 hasConceptScore W4320341405C33923547 @default.
- W4320341405 hasConceptScore W4320341405C37914503 @default.
- W4320341405 hasConceptScore W4320341405C41008148 @default.
- W4320341405 hasConceptScore W4320341405C65909025 @default.
- W4320341405 hasConceptScore W4320341405C82990744 @default.
- W4320341405 hasConceptScore W4320341405C92757383 @default.
- W4320341405 hasLocation W43203414051 @default.
- W4320341405 hasOpenAccess W4320341405 @default.
- W4320341405 hasPrimaryLocation W43203414051 @default.
- W4320341405 hasRelatedWork W1882467697 @default.
- W4320341405 hasRelatedWork W2008139863 @default.
- W4320341405 hasRelatedWork W2283162247 @default.
- W4320341405 hasRelatedWork W2547650990 @default.
- W4320341405 hasRelatedWork W2794771666 @default.
- W4320341405 hasRelatedWork W2921666650 @default.
- W4320341405 hasRelatedWork W2980953096 @default.
- W4320341405 hasRelatedWork W3010888991 @default.
- W4320341405 hasRelatedWork W3201632203 @default.
- W4320341405 hasRelatedWork W4298315644 @default.
- W4320341405 isParatext "false" @default.
- W4320341405 isRetracted "false" @default.
- W4320341405 workType "article" @default.