Bi-CMPStereo uses bidirectional prompting to project event and frame data into each other's domains, creating aligned representations for improved cross-modal stereo matching.
arXiv preprint arXiv:2507.22052 (2025) 4, 11
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
CAMFusion fuses multiview 2D vision-language embeddings via cross-attention and multiview consistency self-supervision to produce better 3D semantic and instance representations, outperforming averaging and reaching SOTA on benchmarks including zero-shot out-of-domain cases.
citing papers explorer
-
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
Bi-CMPStereo uses bidirectional prompting to project event and frame data into each other's domains, creating aligned representations for improved cross-modal stereo matching.
-
Cross-Attentive Multiview Fusion of Vision-Language Embeddings
CAMFusion fuses multiview 2D vision-language embeddings via cross-attention and multiview consistency self-supervision to produce better 3D semantic and instance representations, outperforming averaging and reaching SOTA on benchmarks including zero-shot out-of-domain cases.