3 papers
cs.CV2026
RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models
Omar Alama, Darshil Jariwala, Avigyan Bhattacharya +3
Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing approaches either rely on limited…
cs.CV2025
LLM-RG: Referential Grounding in Outdoor Scenarios using Large Language Models
Pranav Saxena, Avigyan Bhattacharya, Ji Zhang +1
Referential grounding in outdoor driving scenes is challenging due to large scene variability, many visually similar objects, and dynamic elements that complicate resolving natural…
cs.RO2025
RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration
Omar Alama, Avigyan Bhattacharya, Haoyang He +6
Open-set semantic mapping is crucial for open-world robots. Current mapping approaches either are limited by the depth range or only map beyond-range entities in constrained settin…