CV

PhD Researcher

EyeCan.AI

Lecturer

FAST National university of Computer and Emerging Sciences

Graduate Assistant

Ghulam Ishaq Khan Institute of Engineering Sciences and Technology

Software Engineer

The Indus Hospital

PhD

University of Bologna

Computer Science and Engineering

MS

Ghulam Ishaq Khan Institute of Engineering Sciences and Technology

Computer Engineering

BE

Mehran University of Engineering and Technology

Software Engineering

NVS-HO: A Benchmark for Novel View Synthesis of Handheld Objects

International Conference on Pattern Recognition

We propose NVS-HO, the first benchmark designed for novel view synthesis of handheld objects in real-world environments using only RGB inputs. Each object is recorded in two complementary RGB sequences: (1) a handheld sequence, where the object is manipulated in front of a static camera, and (2) a board sequence, where the object is fixed on a ChArUco board to provide accurate camera poses via marker detection. The goal of NVS-HO is to learn a NVS model that captures the full appearance of an object from (1), whereas (2) provides the groundtruth images used for evaluation. To establish baselines, we consider both a classical SfM pipeline and a state-of-the-art pre-trained feed-forward neural network (VGGT) as pose estimators, and train NVS models based on NeRF and Gaussian Splatting. Our experiments reveal significant performance gaps in current methods under unconstrained handheld conditions, highlighting the need for more robust approaches. NVS-HO thus offers a challenging real-world benchmark to drive progress in RGB-based novel view synthesis of handheld objects.

Few-Shot Anomaly Classification by Learning to Inpaint Nominal Images

International Conference on Image Analysis and Processing

Automated inspection is a crucial aspect in modern industrial manufacturing. Despite its importance, the methods used to perform it suffer from the data scarcity intrinsic to the problem, where only a few anomalous samples are usually available. Recently, fine-tuning of foundation inpainting models has been proposed as a solution. The fine-tuned model is then used to inpaint nominal images where areas corresponding to defective masks have been removed. While effective, random pairing sometimes applies the mask on background or logically unfeasible areas. To counteract this phenomenon, we experiment with generating high-resolution defective images inpainting the few available real defects. Since the resulting images would show limited variance in the non-defective parts, we propose to fine-tune another inpainting model to change nominal parts of generated images. Experimental results on the MVTec-AD dataset demonstrate that our method generates images with complementary properties with respect to those produced by the baseline and training on an ensemble of generated data produces a new state of the art result.

AnomalyControl: Few-Shot Anomaly Generation by ControlNet Inpainting

IEEE Access

Quality inspection tasks, i.e., anomaly detection, localization and classification, face the scarcity of non-nominal images in real industrial scenarios. Hence, generative models have been explored as a tool to obtain defective images from few real labelled samples. Despite the fast-increasing quality of such models, generating realistic defective images remains a challenging task due to the same data scarcity problem, which makes it difficult to steer large general-purpose models to produce realistic defects for specific industrial products. In this paper, we show how casting defect generation as inpainting of nominal images and using ControlNet to specialize a state-of-the-art inpainting model based on stable diffusion can be an effective solution for the few-shot anomaly generation task. Extensive experimental results on the MVTec-AD dataset demonstrate that the high quality of the images generated by our method significantly improves the state of the art on downstream anomaly classification.

A novel framework for generating handwritten datasets

Multimedia Tools and Applications

The performance of deep learning algorithms is highly dependent on the size and diversity of data. However, for handwritten character recognition, dataset creation, segmentation, and labeling are time consuming and laborious tasks and not much researched. This work proposes a novel and generic framework which automates the segmentation and labeling processes for handwritten datasets. First, a user collects handwritten glyphs on the proposed form. Next, based on a priori knowledge, local peaks from horizontal and vertical projection functions are computed. This helps in locating and segmenting individual samples automatically. To show the effectiveness of the proposed framework, a dataset of 160,000 samples is collected for an oriental language. We profile the segmentation of samples from one sheet with three approaches: manual, semi-automatic, and the proposed fully automatic approach. Compared to the manual and semi-automatic processes, the proposed approach is 120 × and 65 × faster, respectively. Further, we also present the classification of this dataset by traditional and state-of-the-art machine learning algorithms.