1 citations · 1 across the 9 of their papers we have counts for
4 papers · 1 filter
Image Tokenizers Should Be Trained Between Images
Ole Beißwenger, Jan-Niklas Dihlmann, Hendrik Lensch
Latent diffusion models generate images as codes of an image tokenizer, whose decoder turns them into the pixel image. Recent tokenizers improve how well these codes reconstruct an…
AEGIR: Modeling Area Emitters for Indoor Inverse Rendering using Gaussian Splatting
Mohamed Shawky Sabae, Philipp Langsteiner, Jan-Niklas Dihlmann +1
Inverse rendering requires separating illumination from surface materials, which is highly ambiguous due to their tight coupling in observed images. While Gaussian Splatting is eff…
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Jan-Niklas Dihlmann, Andreas Engelhardt, Simon Donne +2
Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy or avoid. In authoring, this…
ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination
Jan-Niklas Dihlmann, Mark Boss, Simon Donne +3
Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitation…