Amruta Priyadarshan Muthal supervised by Dr. Santosh Ravi Kiran received her Master of Science in Computer Science and Engineering (CSE). Here’s a summary of her research work on Controllable Object Generation:

Modern generative models often struggle to synthesize structured  objects from detailed part specifications.They frequently produce anatomically implausible outputs or hallucinated components. We introduce PLATO, a novel two-stage framework that bridges this gap by enabling precise, part-controlled object generation. The first stage is PLayGen, our novel part layout generator which takes a list of parts and object category as input and synthesizes high fidelity layouts of part bounding boxes.To enhance PLayGen’s ability to learn inter-part relationships,we introduce novel structure-based loss functions. In the second stage, PLayGen’s synthesized layout is used to condition a custom-tuned Control Net-style adapter, enforcing spatial and connectivity constraints. This results in an atomically consistent, high-fidelity object generation containing precisely the user-specified parts. We further propose new part-level evaluation metrics to rigorously quantify adherence to part specifications. Extensive experiments show that PLATO significantly out performs state-of-the-art generative models and produces structurally coherent objects in a controllable manner—marking a step forward in modular, part-driven asset generation.

 December 2025