8 papers
WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priors
Noé Lallouet, Michael Fischer, Elie Michel
Inpainting 3D Gaussian Splatting scenes, a key challenge in 3D editing, requires generating plausible content within a masked region of 3D space. Prior approaches rely on 2D diffus…
ResEdit: Residual embeddings for precise generative image editing
Ahmet Canberk Baykal, Valentin Deschaintre, Yannick Hold-Geoffroy +4
Conditional diffusion image generators can be repurposed for editing through inversion, without the need for large-scale paired fine-tuning data. However, producing high-quality, t…
MAOAM: Unified Object and Material Selection with Vision-Language Models
Jaden Park, Valentin Deschaintre, Jason Kuen +5
Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or c…
UniLight: A Unified Representation for Lighting
Zitian Zhang, Iliyan Georgiev, Michael Fischer +3
Lighting has a strong influence on visual appearance, yet understanding and representing lighting in images remains notoriously difficult. Various lighting representations exist, s…
Fine-Grained Spatially Varying Material Selection in Images
Julia Guerrero-Viu, Michael Fischer, Iliyan Georgiev +4
Selection is the first step in many image editing processes, enabling faster and simpler modifications of all pixels sharing a common modality. In this work, we present a method fo…
Bootstrapping Corner Cases: High-Resolution Inpainting for Safety Critical Detect and Avoid for Automated Flying
Jonathan Lyhs, Lars Hinneburg, Michael Fischer +4
Modern machine learning techniques have shown tremendous potential, especially for object detection on camera images. For this reason, they are also used to enable safety-critical…
Stochastic Gradient Estimation for Higher-order Differentiable Rendering
Zican Wang, Michael Fischer, Tobias Ritschel
We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolut…
SAMa: Material-aware 3D Selection and Segmentation
Michael Fischer, Iliyan Georgiev, Thibault Groueix +3
Decomposing 3D assets into material parts is a common task for artists, yet remains a highly manual process. In this work, we introduce Select Any Material (SAMa), a material selec…