Users appreciate the Face2Scene poster at CVPR 2026 because the lead researcher expresses gratitude toward collaborators from Samsung Research and beyond.
8/ This work was done during my internship at @samsungresearch.
Grateful to all my amazing collaborators: Maitreya Suin, @TristanAA97, Sina Honari, Amanpreet Walia, Iqbal Mohomed, @CSProfKGD, @Babak_Taati, and Alex Levinshtein.
7/ Results show that 𝐅𝐚𝐜𝐞2𝐒𝐜𝐞𝐧𝐞 improves full-scene restoration over strong baselines, with better perceptual quality and more consistent restoration across the face, body, and background.
2/ In 𝐅𝐚𝐜𝐞2𝐒𝐜𝐞𝐧𝐞, we ask a simple question:
Can a restored face tell us how to restore the entire scene? 🧠
3/ Reference-based face restoration can recover high-quality facial details, but it often leaves the body and background degraded.
For human-centric images, restoring only the face is not enough.
6/ Our key contributions:
🔹 Facial degradation as an oracle 🔹 FaDeX for face-derived degradation extraction 🔹 MapNet for multi-scale diffusion conditioning 🔹 InScene, a benchmark for human-centric restoration with identity references
4/ 🧩 Our key idea is to treat the face as a degradation oracle.
We restore the face using identity references, extract degradation cues from the LQ/HQ face pair, and use them to guide full-scene restoration. ✨
5/ 📊 We evaluate in both synthetic and real settings:
🔹 Synthetic scenes with controlled degradations 🔹 Real images with synthetic degradations 🔹 Real captured images with natural degradations This helps test whether face-derived cues generalize beyond controlled benchmarks.
9/ Project page: https://amirhossein-kz.github.io/face2scene/
Paper: https://arxiv.org/abs/2603.16570
#ComputerVision #ImageRestoration #DiffusionModels #FaceRestoration #CVPR2026