From the 1 of 4 papers with an AI index.
- Saarland UniversityDE2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- Chalmers University of TechnologySE1 paper
- Google (Switzerland)CH1 paper
- Google (United States)US1 paper
- Klinikum SaarbrückenDE1 paper
- Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsFR1 paper
- Université de LorraineFR1 paper
- University College LondonGB1 paper
- University of GothenburgSE1 paper
4 papers
PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models
Zhanna Mukhametsharip, Vera Demberg, Varsha Suresh
Large Vision-Language Models (LVLMs) have demonstrated strong performance on multimodal benchmarks, yet it remains unclear whether they genuinely reason about relationships between…
Volumetric Inverse Rendering via Neural Radiative Transfer
Ntumba Elie Nsampi, Adarsh Djeacoumar, Hans-Peter Seidel +2
The paper introduces a method that uses neural fields to jointly estimate the spatially varying optical properties of participating media and the full light field from multi‑view i…
Pseudo-Complex Quantifier Elimination
Nicolas FaroÃ, Nicolas Faroß, Thomas Sturm
We describe the design of a quantifier elimination framework for the complex numbers in the language of ordered rings supplemented with symbols for the imaginary unit, real parts,…
EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering
Jianchun Chen, Yinda Zhang, Rohit Pandey +3
Mixed Reality (MR) headsets promise a future of immersive telepresence where virtual humans blend indistinguishably into real or virtual surroundings. Achieving this vision require…