Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/3ICLR 2026Oral· Deep Learning / Generative Models and Autoencoders

Generative Human Geometry Distribution

Xiangjun Tang · Biao Zhang · Peter Wonka

作者位次 #7/8ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

ShapeGen4D: Towards High Quality 4D Shape Generation from Videos

Jiraphon Yenphraphai · Ashkan Mirzaei · Jianqi Chen · Jiaxu Zou · Sergey Tulyakov · Raymond A. Yeh · Peter Wonka · Chaoyang Wang

多模态OpenReview

作者位次 #4/4ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation

Zhenyu Li · Wenqing Cui · Shariq Bhat · Peter Wonka

多模态OpenReview

作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition

Human Geometry Distribution for 3D Animation Generation

Xiangjun Tang · Biao Zhang · Peter Wonka

多模态社会与人本OpenReview 项目页

作者位次 #7/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Any Resolution Any Geometry: From Multi-View To Multi-Patch

Wenqing Cui · Zhenyu Li · Mykola Lavreniuk · Jian Shi · Ramzi Idoughi · Xiangjun Tang · Peter Wonka

多模态OpenReview 项目页

作者位次 #8/9CVPR 2026Poster· Computer Vision & Pattern Recognition

CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models

Vladislav Pyatov · Gleb Bobrovskikh · Saveliy Galochkin · Nikita Boldyrev · Oleg Voynov · Alexander Filippov · Gonzalo Ferrer · Peter Wonka · Evgeny Burnaev

多模态数据与预训练代码OpenReview 项目页

作者位次 #6/7CVPR 2026Poster· Computer Vision & Pattern Recognition

PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding

Souhail Hadgi · Bingchen Gong · Ramana Sundararaman · Emery Pierson · Lei Li · Peter Wonka · Maks Ovsjanikov

对齐与偏好多模态OpenReview 项目页

作者位次 #10/11CVPR 2026Poster· Computer Vision & Pattern Recognition

One Algorithm to Align Them All

Boyi Pang · Savva Ignatyev · Vladimir Ippolitov · Ramil Khafizov · Yurii Melnik · Oleg Voynov · Maksim Nakhodnov · Aibek Alanov · Xiaopeng Fan · Peter Wonka · Evgeny Burnaev

对齐与偏好多模态OpenReview 项目页

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

LumiX: Structured and Coherent Text-to-Intrinsic Generation

Xu Han · Biao Zhang · Xiangjun Tang · Xianzhi Li · Peter Wonka

多模态OpenReview 项目页

作者位次 #7/8CVPR 2026Poster· Computer Vision & Pattern Recognition

EasyV2V: A High-quality Instruction-based Video Editing Framework

Jinjie Mai · Chaoyang Wang · Gordon Guocheng Qian · Willi Menapace · Sergey Tulyakov · Bernard Ghanem · Peter Wonka · Ashkan Mirzaei

多模态OpenReview 项目页

作者位次 #9/14CVPR 2026Spotlight· Computer Vision & Pattern Recognition

EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR

Zhenyu Li · Sai Kumar Dwivedi · Filip Maric · Carlos Chacón · Nadine Bertsch · Filippo Arcadu · Tomas Hodan · Michael Ramamonjisoa · Peter Wonka · Amy Zhao · Robin Kips · Cem Keskin · Anastasia Tkach · Chenhongyi Yang

多模态社会与人本OpenReview 项目页

作者位次 #4/4CVPR 2026Oral· Computer Vision & Pattern Recognition

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

Jianqi Chen · Biao Zhang · Xiangjun Tang · Peter Wonka

推理多模态OpenReview 项目页

作者位次 #4/4SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

Ref-DGS: Reflective Dual Gaussian Splatting

Ningjing Fan · Yiqun Wang · Dong-ming Yan · Peter Wonka

OpenReview

作者位次 #6/6SIGGRAPH 2026Journal· Computer Graphics (TOG Journal Track)

DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation

Jian Shi · Qian Wang · Zhenyu Li · Wenqing Cui · Ramzi Idoughi · Peter Wonka

多模态OpenReview

Peter Wonka

获取完整研究档案

联系方式

2026 顶会论文

Generative Human Geometry Distribution

ShapeGen4D: Towards High Quality 4D Shape Generation from Videos

PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation

Human Geometry Distribution for 3D Animation Generation

Any Resolution Any Geometry: From Multi-View To Multi-Patch

CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models

PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding

One Algorithm to Align Them All

LumiX: Structured and Coherent Text-to-Intrinsic Generation

EasyV2V: A High-quality Instruction-based Video Editing Framework

EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

Ref-DGS: Reflective Dual Gaussian Splatting

DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation

常见合作者