PanoSAM2 adapts SAM2 with a Pano-Aware Decoder, Distortion-Guided Mask Loss, and Long-Short Memory Module to improve 360 video object segmentation, reporting +5.6 and +6.7 gains over base SAM2 on two benchmarks.
arXiv preprint arXiv:2509.11772 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Seg2Track++ integrates SAM2 with Mask Centroid Distance, Confidence-Aware Cost Modulation, and a Bernoulli-filter-based Probabilistic Track Validation module to improve track consistency in MOTS.
citing papers explorer
-
PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation
PanoSAM2 adapts SAM2 with a Pano-Aware Decoder, Distortion-Guided Mask Loss, and Long-Short Memory Module to improve 360 video object segmentation, reporting +5.6 and +6.7 gains over base SAM2 on two benchmarks.
-
Seg2Track++: Probabilistic Track Validation and Data Association for Multi-Object Tracking and Segmentation
Seg2Track++ integrates SAM2 with Mask Centroid Distance, Confidence-Aware Cost Modulation, and a Bernoulli-filter-based Probabilistic Track Validation module to improve track consistency in MOTS.