Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
COMBAT: Conditional World Models for Behavioral Agent Training
Anmol Agarwal, Pranay Meshram, Sumer Singh +5
Recent advances in video generation have spurred the development of world models capable of simulating 3D-consistent environments and interactions with static objects. However, a s…
cs.CV2025
QAL: A Loss for Recall Precision Balance in 3D Reconstruction
Pranay Meshram, Yash Turkar, Kartikeya Singh +3
Volumetric learning underpins many 3D vision tasks such as completion, reconstruction, and mesh generation, yet training objectives still rely on Chamfer Distance (CD) or Earth Mov…
cs.CV2024
Empir3D : A Framework for Multi-Dimensional Point Cloud Assessment
Yash Turkar, Pranay Meshram, Christo Aluckal +2
Advancements in sensors, algorithms, and compute hardware have made 3D perception feasible in real time. Current methods to compare and evaluate the quality of a 3D model, such as…