🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

.Biao Zhang presenting our 3DShape2VecSet paper at #SIGGRAPH2023!!! We propose a 3D representation for neural fields and generative diffusion models for figh-fidelity shape generation. Super cool work from Peter Wonka's group in collab with Jiapeng Tang.

ICCV 2023: "SATR: Zero-Shot Semantic Segmentation of 3D Shapes". Ahmed Abdelreheem (Ahmed Abdelreheem), Ivan Skorokhodov (Ivan Skorokhodov), Maks Ovsjanikov, Peter Wonka. An algorithm harnessing pret-trained 2D models for 3D mesh segmentation. Project page: samir55.github.io/SATR/"

Zero-Shot 3D Shape Correspondence, ACM Siggraph Asia 2023 Ahmed Abdelreheem (Ahmed Abdelreheem), Abdelrahman Eldesokey (Abdo Eldesokey), Maks Ovsjanikov, Peter Wonka samir55.github.io/3dshapematch/ Computing correspondences between dissimilar shapes using pretrained language models

State of the Art on Diffusion Models for Visual Computing (Ryan Po Yifan Wang Vlad Golyanik Kfir Aberman Jon Barron Amit H. Bermano Eric Chan Tali Dekel Aleksander Holynski Angjoo Kanazawa Lingjie Liu Ben Mildenhall Matthias Niessner Gordon Wetzstein) arxiv.org/abs/2310.07204

We propose a new type of diffusion model that diffuses continuous functions: Functional Diffusion. Biao Zhang (Biao Zhang ) and Peter Wonka. arXiv arxiv.org/abs/2311.15435 1zb.github.io/functional-dif…

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features Thomas Wimmer, Peter Wonka, Maks Ovsjanikov arxiv.org/abs/2311.18113 wimmerth.github.io/back-to-3d.html Projected 2D features + geodesic distance optimization gives new SOTA for few-shot keypoint detection

A framework to control diffusion-generated images using boxes as proxies for geometry (together with Shariq Farooq Bhat Shariq Farooq and Niloy Mitra)

A framework to advance SOTA in high-resolution depth estimation (Zhenyu Li just joined as a new PhD student in August.)

Commencement at KAUST (⁦KAUST CEMSE⁩ ⁦Ivan Skorokhodov⁩ ⁦Anna Frühstück⁩ ⁦Biao Zhang⁩ and Wamiq and Yanze) Anna was selected as commencement speaker this year!

I collaborated with several colleagues from CAS and Sichuan on a survey on image and video inpaiting: arxiv.org/abs/2401.03395

Our image-to-3D generation work Magic123 gets accepted at #ICLR2024. It is a collaborated work among KAUST Computer Vision Lab (IVUL) led by my supervisor Bernard Ghanem, my internship team at Snapchat led by Sergey Tulyakov, Abdullah Hamdi from Visual Geometry Group (VGG), and Peter Wonka from KAUST VCC.

LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts Hanan Gani (Hanan @CVPR 2025 🇺🇸), Shariq Farooq Bhat (Shariq Farooq), Muzammal Naseer, Salman Khan, Peter Wonka ICLR 2024 hananshafi.github.io/llm-blueprint/

Join the #KAUST Global Fellowship Program, an incredible opportunity for exceptional postdocs with groundbreaking ideas to advance Saudi's research priorities. The program offers access to cutting-edge research tools, top-notch facilities and expert mentorship.

Happy to share that our Vivid-Zoo paper has been accepted at #NeurIPS2024. The paper is collaborated with zc Wenxuan Zhu Biao Zhang Peter Wonka Bernard Ghanem

📢𝐆𝐞𝐨𝐦𝐞𝐭𝐫𝐲 𝐃𝐢𝐬𝐭𝐫𝐢𝐛𝐮𝐭𝐢𝐨𝐧𝐬 We propose to represent general geometries as distributions using diffusion models. project site: 1zb.github.io/GeomDist/ arxiv: arxiv.org/abs/2411.16076 dataset: huggingface.co/datasets/Zbalp… Collaboration with Jing Ren and Peter Wonka

T-3DGS: Removing Transient Objects for 3D Scene Reconstruction Vadim Pryadilshchikov, Alexander Markin, Artem Komarichev, Ruslan Rakhimov, Peter Wonka, Evgeny Burnaev tl;dr: unsupervised transient detector and transient mask propagation arxiv.org/abs/2412.00155

Our preprint on deep learning based high-throughout human #blastoid classification is out It helps unbiased quality assessment of a large number of blastoids thx for Prof Peter Wonka and his team’s collaboration KAUST BESE KAUST Research bioRxiv biorxiv.org/cgi/content/sh…

📢📢 𝐏𝐫𝐄𝐝𝐢𝐭𝐨𝐫𝟑𝐃: 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐏𝐫𝐞𝐜𝐢𝐬𝐞 𝟑𝐃 𝐒𝐡𝐚𝐩𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 📢📢 We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is. Using a quickly brushed mask and a

Update about the 4th Monocular Depth Estimation Workshop at #CVPR2025: 🎉 Website is LIVE! (link below) 🎉 Keynotes: Peter Wonka (Peter Wonka), Yiyi Liao (Yiyi Liao), and Konrad Schindler 🎉 Challenge updates: new prediction types, baselines & metrics

Our paper, "Training-free Video Semantic Segmentation based on Diffusion Models," was accepted at CVPR 2025! A great collaboration between KAUST and MPI. Image diffusion models are powerful for image generation and serve as strong backbones with rich semantic understanding.