Searcharxiv⌕ Search

arXiv subjects

Arnav Samal

Publications and source records attributed to Arnav Samal.

2 recordsLinked to original sources

SurfScaff3D: Bridging Geometric and Semantic Representations for LLM-based 3D Object Generation

Creating high-quality 3D content has traditionally required specialist expertise and experience with complex tools. The growing ecosystem of AI-assisted creativity demands accessible and intuitive 3D generation systems. Recent advances in Large Language Models (LLMs) offer promising directions, yet extending their generative capabilities to 3D remains fundamentally challenging because existing 3D representations are not naturally compatible with language-based reasoning. Current approaches either depend on expensive fine-tuning or impose restrictive structural priors that sacrifice expressiveness and exclude organic shapes. We argue that the mismatch between LLM-native reasoning and conventional 3D parameterizations is a core bottleneck of LLM-driven 3D generation. To address this, we introduce the Hierarchical Patch Scaffold (HPS), a representation designed around semantically meaningful, interpretable part-level abstractions that are naturally understood by both humans and LLMs, enabling expressive, editable, and open-domain 3D generation without imposing restrictive geometric priors or expensive fine-tuning. Building upon HPS, we introduce SurfScaff3D, an interactive framework for text and image-to-3D generation. HPS inherits the flexibility of B-spline patches, while exposing an interface that leverages open-world capabilities of foundation models to reliably generate 3D. Its hierarchical part-level semantic labels enable targeted, natural-language edits at any level of granularity without re-running generation. Further, HPS offers explicit per-patch control over surface detail, enabling more expressive geometry capable of representing arbitrary objects. Extensive experiments against state-of-the-art LLM-based 3D generation methods demonstrate strong geometric fidelity, semantic alignment, and flexible editing across diverse object categories.

cs.CV↗

CapsoNet: A CNN-Transformer Ensemble for Multi-Class Abnormality Detection in Video Capsule Endoscopy

We present CapsoNet, a deep learning framework developed for the Capsule Vision 2024 Challenge, designed to perform multi-class abnormality classification in video capsule endoscopy (VCE) frames. CapsoNet leverages an ensemble of convolutional neural networks (CNNs) and transformer-based architectures to capture both local and global visual features. The model was trained and evaluated on a dataset of over 50,000 annotated frames spanning ten abnormality classes, sourced from three public and one private dataset. To address the challenge of class imbalance, we employed focal loss, weighted random sampling, and extensive data augmentation strategies. All models were fully fine-tuned to maximize performance within the ensemble. CapsoNet achieved a balanced accuracy of 86.34 percent and a mean AUC-ROC of 0.9908 on the official validation set, securing Team Seq2Cure 5th place in the competition. Our implementation is available at http://github.com/arnavs04/capsule-vision-2024

cs.CV↗