activity
20242026
most citedDon't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM

1 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2026

KISS-GS: 3D Gaussian Splatting Compression Kept Simple

Wieland Morgenstern, Friedrich Elias Branschke, Florian Fleischmann +5

Scene reconstruction with 3D Gaussian Splatting (3DGS) has become common, however deployment remains painful as the uncompressed file sizes can be massive. Current 3DGS compression…

cs.CV2026

COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editing

Florian Barthel, Shalini De Mello, Koki Nagano +3

Recent 3D Gaussian Splatting (3DGS) GANs for human heads synthesize and render photorealistic 3D models in real-time and offer a vast variety in identity and appearance. However, c…

cs.CV2025★ 1 cited

EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point Clouds

Yuanchao Yue, Hui Yuan, Qinglong Miao +3

Cross-modal data registration has long been a critical task in computer vision, with extensive applications in autonomous driving and robotics. Accurate and robust registration met…

cs.LG2025

Permutation Learning with Only N Parameters: From SoftSort to Self-Organizing Gaussians

Kai Uwe Barthel, Florian Barthel, Peter Eisert

Sorting and permutation learning are key concepts in optimization and machine learning, especially when organizing high-dimensional data into meaningful spatial layouts. The Gumbel…

cs.LG2024★ 1 cited

Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM

Maximilian Mews, Ansar Aynetdinov, Vivian Schiller +2

While recent advancements in machine learning, such as LLMs, are revolutionizing software development and creative industries, they have had minimal impact on engineers designing m…