4 papers
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…
ReasonX: MLLM-Guided Intrinsic Image Decomposition
Alara Dirik, Tuanfeng Wang, Duygu Ceylan +2
Intrinsic image decomposition aims to separate images into physical components such as albedo, depth, normals, and illumination. While recent diffusion- and transformer-based model…
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling
Alara Dirik, Tuanfeng Wang, Duygu Ceylan +2
We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion m…
SuperGaussian: Repurposing Video Models for 3D Super Resolution
Yuan Shen, Duygu Ceylan, Paul Guerrero +4
We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet m…