arXiv subjects

Fadlullah Raji

Publications and source records attributed to Fadlullah Raji.

3 recordsLinked to original sources

arXiv2026

Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models

Generating 3D models has traditionally been a complex task requiring specialized expertise. While recent advances in generative AI have sought to automate this process, existing methods produce non-editable representation, such as meshes or point clouds, limiting their adaptability for iterative design. In this paper, we introduce Proc3D, a system designed to generate editable 3D models while enabling real-time modifications. At its core, Proc3D introduces procedural compact graph (PCG), a graph representation of 3D models, that encodes the algorithmic rules and structures necessary for generating the model. This representation exposes key parameters, allowing intuitive manual adjustments via sliders and checkboxes, as well as real-time, automated modifications through natural language prompts using Large Language Models (LLMs). We demonstrate Proc3D's capabilities using two generative approaches: GPT-4o with in-context learning (ICL) and a fine-tuned LLAMA-3 model. Experimental results show that Proc3D outperforms existing methods in editing efficiency, achieving more than 400x speedup over conventional approaches that require full regeneration for each modification. Additionally, Proc3D improves ULIP scores by 28%, a metric that evaluates the alignment between generated 3D models and text prompts. By enabling text-aligned 3D model generation along with precise, real-time parametric edits, Proc3D facilitates highly accurate text-based image editing applications.

cs.GR↗

arXiv2026

Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy

Conventional imaging requires a line of sight to create accurate visual representations of a scene. In certain circumstances, however, obtaining a suitable line of sight may be impractical, dangerous, or even impossible. Non-line-of-sight (NLOS) imaging addresses this challenge by reconstructing the scene from indirect measurements. Recently, passive NLOS methods that use an ordinary photograph of the subtle shadow cast onto a visible wall by the hidden scene have gained interest. These methods are currently limited to 1D or low-resolution 2D color imaging or to localizing a hidden object whose shape is approximately known. Here, we generalize this class of methods and demonstrate a 3D reconstruction of a hidden scene from an ordinary NLOS photograph. To achieve this, we propose a novel reformulation of the light transport model that conveniently decomposes the hidden scene into \textit{light-occluding} and \textit{non-light-occluding} components to yield a separable non-linear least squares (SNLLS) inverse problem. We develop two solutions: A gradient-based optimization method and a physics-inspired neural network approach, which we call Soft Shadow diffusion (SSD). Despite the challenging ill-conditioned inverse problem encountered here, our approaches are effective on numerous 3D scenes in real experimental scenarios. Moreover, SSD is trained in simulation but generalizes well to unseen classes in simulation and real-world NLOS scenes. SSD also shows surprising robustness to noise and ambient illumination.

cs.CV↗

arXiv2022

Optimal wireless rate and power control in the presence of jammers using reinforcement learning

Future wireless networks require high throughput and energy efficiency. This paper studies using Reinforcement Learning (RL) to do transmission rate and power control for maximizing a joint reward function consisting of both throughput and energy consumption. We design the system state to include factors that reflect packet queue length, interference from other nodes, quality of the wireless channel, battery status, etc. The reward function is normalized and does not involve unit conversion. It can be used to train three different types of agents: throughput-critical, energy-critical, and throughput and energy balanced. Using the NS-3 network simulation software, we implement and train these agents in an 802.11ac network with the presence of a jammer. We then test the agents with two jamming nodes interfering with the packets received at the receiver. We compare the performance of our RL optimal policies with the popular Minstrel rate adaptation algorithm: our approach can achieve (i) higher throughput when using the throughput-critical reward function; (ii) lower energy consumption when using the energy-critical reward function; and (iii) higher throughput and slightly higher energy when using the throughput and energy balanced reward function. Although our discussion is focused on 802.11ac networks, our method is readily applicable to other types of wireless networks.

cs.NI↗