Peter Wonka
@peter_wonka
Followers
984
Following
31
Media
22
Statuses
49
Prof. of Computer Science at KAUST | Computer Vision, Machine Learning, Computer Graphics, Deep Learning
Thuwal, Saudi Arabia
Joined November 2021
RT @WindVChen: ๐ขV2M4 (Accepted by ICCV 2025). We reconstruct 4D mesh animations from a single video with consistency in pose, appearance,โฆ.
0
2
0
RT @ashmrz10: [1/9] ๐ We introduce 4Real-Video-V2, a method that can generate 4D scenes from a simple text prompt, viewable from any angleโฆ.
0
26
0
RT @VcaiMpi: Our paper, "Training-free Video Semantic Segmentation based on Diffusion Models," was accepted at CVPR 2025! . A great collaboโฆ.
0
12
0
RT @AntonObukhov1: Update about the 4th Monocular Depth Estimation Workshop at #CVPR2025: .๐ Website is LIVE! (link below).๐ Keynotes: Peteโฆ.
0
15
0
RT @Mo_Li_KAUST: Our preprint on deep learning based high-throughout human #blastoid classification is out It helps unbiased quality assessโฆ.
0
2
0
RT @MattNiessner: ๐ข๐ข ๐๐ซ๐๐๐ข๐ญ๐จ๐ซ๐๐: ๐
๐๐ฌ๐ญ ๐๐ง๐ ๐๐ซ๐๐๐ข๐ฌ๐ ๐๐ ๐๐ก๐๐ฉ๐ ๐๐๐ข๐ญ๐ข๐ง๐ ๐ข๐ข. We propose a training-free 3D shape editing approach that rapidly anโฆ.
0
45
0
RT @zhenjun_zhao: T-3DGS: Removing Transient Objects for 3D Scene Reconstruction. Vadim Pryadilshchikov, Alexander Markin, Artem Komarichevโฆ.
0
6
0
RT @_BiaoZhang: ๐ข๐๐๐จ๐ฆ๐๐ญ๐ซ๐ฒ ๐๐ข๐ฌ๐ญ๐ซ๐ข๐๐ฎ๐ญ๐ข๐จ๐ง๐ฌ.We propose to represent general geometries as distributions using diffusion models. project site:โฆ.
0
31
0
RT @summerie9: Happy to share that our Vivid-Zoo paper has been accepted at #NeurIPS2024. The paper is collaborated with.@1zhengcheng.@Wenโฆ.
0
4
0
RT @KAUST_News: Join the #KAUST Global Fellowship Program, an incredible opportunity for exceptional postdocs with groundbreaking ideas toโฆ.
0
25
0
LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts.Hanan Gani (@hanan_shafi29), Shariq Farooq Bhat (@shariq_farooq), Muzammal Naseer, Salman Khan, Peter Wonka.ICLR 2024.
0
3
25
RT @guocheng_qian: Our image-to-3D generation work Magic123 gets accepted at #ICLR2024. It is a collaborated work among @KaustVision led bโฆ.
0
4
0
I collaborated with several colleagues from CAS and Sichuan on a survey on image and video inpaiting:.
arxiv.org
Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the...
0
0
20
Commencement at KAUST (โฆ@cemseKAUSTโฉ โฆ@isskoroโฉ โฆ@farnuneaโฉ โฆ@_BiaoZhangโฉ and Wamiq and Yanze) Anna was selected as commencement speaker this year!
1
1
34
A framework to advance SOTA in high-resolution depth estimation (@zhenyu_li9955 just joined as a new PhD student in August.).
Check our new work PatchFusion! It estimates high-resolution metric depth with intricate details for high-resolution input image. Zhenyu Li, Shariq Farooq Bhat (@shariq_farooq), Peter Wonka (@peter_wonka). Webpage:
1
7
74
A framework to control diffusion-generated images using boxes as proxies for geometry (together with Shariq Farooq Bhat @shariq_farooq and Niloy Mitra).
LooseControl: Lifting ControlNet for Generalized Depth Conditioning @Gradio demo is out on @huggingface . demo: run with docker: duplicate space with private gpu and no queue: present LooseControl to allow
0
4
26
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features.Thomas Wimmer, Peter Wonka, Maks Ovsjanikov. Projected 2D features + geodesic distance optimization gives new SOTA for few-shot keypoint detection
0
17
69
We propose a new type of diffusion model that diffuses continuous functions:. Functional Diffusion. Biao Zhang (@_BiaoZhang ) and Peter Wonka. arXiv.
4
54
360
State of the Art on Diffusion Models for Visual Computing.(@Po_lhr @toomanyyifans @VGolyanik @AbermanKfir @jon_barron @bermano_h @ericryanchan @talidekel @holynski_ @akanazawa @LingjieLiu1 @BenMildenhall @MattNiessner @GordonWetzstein).
0
10
68
Zero-Shot 3D Shape Correspondence, ACM Siggraph Asia 2023. Ahmed Abdelreheem (@aabdelreheem95), Abdelrahman Eldesokey (@Abdo_Eldesokey), Maks Ovsjanikov, Peter Wonka. Computing correspondences between dissimilar shapes using pretrained language models
1
12
61