4 papers
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
Saikat Dutta, Biplab Banerjee, Hamid Rezatofighi
Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inferenc…
Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactions
Sandika Biswas, Qianyi Wu, Biplab Banerjee +1
Real-world human-built environments are highly dynamic, involving multiple humans and their complex interactions with surrounding objects. While 3D geometry modeling of such scenes…
AerOSeg: Harnessing SAM for Open-Vocabulary Segmentation in Remote Sensing Images
Saikat Dutta, Akhil Vasim, Siddhant Gole +2
Image segmentation beyond predefined categories is a key challenge in remote sensing, where novel and unseen classes often emerge during inference. Open-vocabulary image Segmentati…
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
Sandika Biswas, Qianyi Wu, Biplab Banerjee +1
Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable enti…