3 papers
cs.CV2026
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation
Anindya Mondal, Sauradip Nag, Anjan Dutta
ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-spe…
cs.CV2026
CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance
Anindya Mondal, Ayan Banerjee, Sauradip Nag +3
Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework t…
cs.CV2025
OmniCount: Multi-label Object Counting with Semantic-Geometric Priors
Anindya Mondal, Sauradip Nag, Xiatian Zhu +1
Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adapta…