Metraipolis › archive › dc_b299dedf09aa
RCFormer: Reliability-aware Context Transformer for Occlusion-Robust Facial Landmark Detection — arXiv:2611.01822
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01822
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:54:44.858Z
- SHA-256 of the archived text
19bb278bfaff322e5f96a56989dea857164f0ec0636fb7597c740fab13703a50- Stable URL of this page
https://metraipolis.com/documento/dc_b299dedf09aa
How to cite
RCFormer: Reliability-aware Context Transformer for Occlusion-Robust Facial Landmark Detection — arXiv:2611.01822 — arXiv (en), https://arxiv.org/abs/2611.01822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b299dedf09aa (Metraipolis archive dc_b299dedf09aa, sha256 19bb278bfaff322e5f96a56989dea857164f0ec0636fb7597c740fab13703a50)
BibTeX
@misc{dcb299dedf09aa,
title = {RCFormer: Reliability-aware Context Transformer for Occlusion-Robust Facial Landmark Detection — arXiv:2611.01822},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01822},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b299dedf09aa; sha256 19bb278bfaff322e5f96a56989dea857164f0ec0636fb7597c740fab13703a50},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Facial landmark detection has advanced substantially under regular imaging conditions, yet occlusion, poor illumination, and large pose changes remain major sources of error because local facial evidence can become incomplete or misleading. Context-guided latent patch recovery offers a promising way to address this issue by inferring unreliable patch representations from surrounding facial context before heatmap prediction. However, the recovered context can itself be unreliable when it is weakly adapted to the input face, influenced by corrupted neighboring patches, or blended without preserving local spatial coherence. We propose RCFormer, a Reliability-aware Context Transformer for occlusion-robust facial landmark detection. RCFormer strengthens latent patch recovery with three reliability-oriented components: visible-context conditioning (VCC), which adapts the context representation using a visibility-weighted global facial summary; visibility-guided context aggregation (VGCA), which reduces the influence of unreliable source patches during attention; and spatial residual correction (SRC), which refines blended latent features using neighboring patch information. The recovered heatmaps are then used as reliability-aware structural cues for existing landmark detection networks. Experiments show that RCFormer improves heatmap recovery and achieves strong landmark localization results on the WFLW, COFW, and 300W datasets. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.01822 — 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 2026-11-03T18:16:52.958Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).