activity
20242026
collaborators

9 papers

cs.CV2026

Control-DINO: Feature Space Conditioning for Controllable Image-to-Video Diffusion

Edoardo A. Dominici, Thomas Deixelberger, Konstantinos Vardis +1

Video diffusion models have recently been applied with success to problems in content generation, novel view synthesis, and, more broadly, world simulation. Many applications in ge…

cs.CV2026

Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation

Stefan Ainetter, Thomas Deixelberger, Edoardo A. Dominici +3

We present GuidedSceneGen, a text-to-3D generation framework that produces metrically accurate, globally consistent, and semantically interpretable indoor scenes. Unlike prior text…

cs.CV2026

Confidence-Based Mesh Extraction from 3D Gaussians

Lukas Radl, Felix Windisch, Andreas Kurz +3

Recently, 3D Gaussian Splatting (3DGS) greatly accelerated mesh extraction from posed images due to its explicit representation and fast software rasterization. While the addition…

cs.CV2026

Autoregressive Appearance Prediction for 3D Gaussian Avatars

Michael Steiner, Zhang Chen, Alexander Richard +3

A photorealistic and immersive human avatar experience demands capturing fine, person-specific details such as cloth and hair dynamics, subtle facial expressions, and characteristi…

cs.LG2026

From ex(p) to poly: Gaussian Splatting with Polynomial Kernels

Joerg H. Mueller, Martin Winter, Markus Steinberger

Recent advancements in Gaussian Splatting (3DGS) have introduced various modifications to the original kernel, resulting in significant performance improvements. However, many of t…

cs.GR2026

Pi-GS: Sparse-View Gaussian Splatting with Dense π^3 Initialization

Manuel Hofer, Markus Steinberger, Thomas Köhler

Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering and rapid training without comprom…