Metraipolis › archive › dc_2c171a676831
MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection — arXiv:2611.06282
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06282
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:50.440Z
- SHA-256 of the archived text
2648a8fb5aaa5ffb15b9a15c7ba382278dd02c5c2bc52fae4e74a7c9668f681b- Stable URL of this page
https://metraipolis.com/documento/dc_2c171a676831
How to cite
MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection — arXiv:2611.06282 — arXiv (en), https://arxiv.org/abs/2611.06282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c171a676831 (Metraipolis archive dc_2c171a676831, sha256 2648a8fb5aaa5ffb15b9a15c7ba382278dd02c5c2bc52fae4e74a7c9668f681b)
BibTeX
@misc{dc2c171a676831,
title = {MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection — arXiv:2611.06282},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06282},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c171a676831; sha256 2648a8fb5aaa5ffb15b9a15c7ba382278dd02c5c2bc52fae4e74a7c9668f681b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view. Recent transformer-based detectors learn geometry purely from image features and 3D box annotations, lacking the high-level semantic priors that vision-language models (VLMs) acquire from large-scale pretraining. VLMs offer such priors, but deploying one directly as a detector is impractical due to its heavy inference cost. We propose MonoLaDN, a language-guided denoising framework that transfers the geometric reasoning of a VLM into a monocular 3D detector while keeping the deployed model purely vision-based. During training, a frozen VLM produces structured reasoning about each object's occlusion, depth, dimension, and angle from the image and its ground-truth boxes. We encode this reasoning into queries, perturb them with noise, and train the detector to reconstruct the clean reasoning. Reconstructing the corrupted reasoning forces the detector's depth-guided features to internalize the VLM's geometric priors, so this knowledge remains available even after the reasoning path is discarded at inference, adding no latency or parameters to the deployed model. Experiments on KITTI 3D and nuScenes show that MonoLaDN consistently outperforms state-of-the-art detectors and generalizes well to new domains. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.06282 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:12:49.052Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).