arXiv subjects

Arjun Mehra

Publications and source records attributed to Arjun Mehra.

2 recordsLinked to original sources

arXiv2026

What Makes a 3D Scene Editable? A Factorized Benchmark of Fidelity, Locality, Consistency, and Preservation

Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent across views. We introduce EditBench3D, a representation-agnostic benchmark that treats editing as controlled information replacement. It evaluates four complementary properties: instruction fidelity, spatial locality, cross-view consistency, and preservation of non-target content. The protocol combines visibility-aware 3D target supports, paired descriptions, held-out cameras, and five edit families covering appearance, material, geometry, and object-level changes. We evaluate eight representative NeRF, 3D Gaussian Splatting, hybrid, and proxy-based editors on 240 scene-edit pairs. The study shows that semantic fidelity is only weakly associated with the other editing properties, and that no single method is optimal across all dimensions. Explicit Gaussian editors offer a strong overall balance, whereas direct proxy manipulation provides the most conservative edits at the cost of open-ended fidelity. These findings support reporting editability as a multi-objective profile rather than a single semantic score.

cs.CV↗

arXiv2023

Federated Learning for Wireless Applications: A Prototype

Wireless embedded edge devices are ubiquitous in our daily lives, enabling them to gather immense data via onboard sensors and mobile applications. This offers an amazing opportunity to train machine learning (ML) models in the realm of wireless devices for decision-making. Training ML models in a wireless setting necessitates transmitting datasets collected at the edge to a cloud parameter server, which is infeasible due to bandwidth constraints, security, and privacy issues. To tackle these challenges, Federated Learning (FL) has emerged as a distributed optimization approach to the decentralization of the model training process. In this work, we present a novel prototype to examine FL's effectiveness over bandwidth-constrained wireless channels. Through a novel design consisting of Zigbee and NI USRP devices, we propose a configuration that allows clients to broadcast synergistically local ML model updates to a central server to obtain a generalized global model. We assess the efficacy of this prototype using metrics such as global model accuracy and time complexity under varying conditions of transmission power, data heterogeneity and local learning.

cs.IT↗