Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4ECCV 2026Poster

Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow

Shenhan Qian · Ganlin Zhang · Elliott (Shangzhe) Wu · Daniel Cremers

Geometry, Localization, Matching & MotionOpenReview

作者位次 #7/9ECCV 2026Poster

SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models

Jingfeng Mao · Xuyang Chen · Qilin Zhang · Oussema Dhaouadi · Guangming Wang · Brian Sheil · Daniel Cremers · Yan Xia · Olaf Wysocki

Geometry, Localization, Matching & MotionOpenReview

作者位次 #7/7ECCV 2026Poster

Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments

Michael Schleiss · Henry Hölzemann · Fahmi Rouatbi · Torsten Fiolka · Thomas Pany · Roger Förstner · Daniel Cremers

数据与预训练Geometry, Localization, Matching & MotionOpenReview

作者位次 #6/6ECCV 2026Poster

Kinematics-Agnostic 3D Human Motion Prediction via Equivariant Latent Diffusion

Cecilia Curreli · Florian Hofherr · Dominik Muhle · Abhishek Saroha · Riccardo Marin · Daniel Cremers

可解释性社会与人本3D Graphics and Geometric RepresentationsOpenReview

作者位次 #6/6ECCV 2026Poster

OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos

Oussema Dhaouadi · Zuria Bauer · Johannes Meier · Olaf Wysocki · Marc Pollefeys · Daniel Cremers

Geometry, Localization, Matching & MotionOpenReview

作者位次 #6/8ECCV 2026Poster

ECHO: Ego-centric Modeling of Human-Object Interactions

Ilya A. Petrov · Vladimir Guzov · Riccardo Marin · Emre Aksan · Xu Chen · Daniel Cremers · Thabo Beeler · Gerard Pons-Moll

多模态社会与人本Video Generation, Avatars & Dynamic WorldsOpenReview

作者位次 #10/10ECCV 2026Poster

LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection

Johannes Meier · Jonathan Michel · Oussema Dhaouadi · Yung-Hsu Yang · Christoph Reich · Zuria Bauer · Stefan Roth · Marc Pollefeys · Jacques Kaiser · Daniel Cremers

强化学习与后训练Recognition, Tracking, Re-ID & Anomaly DetectionOpenReview

作者位次 #3/4ECCV 2026Oral

PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

Aymeric Fleith · Julian Zirbel · Daniel Cremers · Niclas Zeller

多模态Computational Imaging, Shape Recovery and Camera GeometryOpenReview

作者位次 #7/7ECCV 2026Poster

SegFly: A 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale

Markus Gross · Sai Bharadhwaj Matha · Rui Song · Viswanathan Muthuveerappan · Conrad Christoph · Julius Huber · Daniel Cremers

3D Reconstruction, Registration and Scene ModelingOpenReview

作者位次 #3/3ECCV 2026Poster

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

Niklas Schweiger · Karnik Ram · Daniel Cremers

对齐与偏好多模态检索与知识Low-Level Vision, Restoration & Generative PriorsOpenReview

作者位次 #5/5ECCV 2026Spotlight

VOCA: Visual Odometry with Codec Awareness

Nouri Alexander Hilscher · Mateo de Mayo · Dominik Muhle · Christoph Otten genannt Hermes · Daniel Cremers

多模态Embodied AI, Robotics & Autonomous DrivingOpenReview

Daniel Cremers

获取完整研究档案

联系方式

2026 顶会论文

Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow

SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models

Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments

Kinematics-Agnostic 3D Human Motion Prediction via Equivariant Latent Diffusion

OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos

ECHO: Ego-centric Modeling of Human-Object Interactions

LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection

PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

SegFly: A 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

VOCA: Visual Odometry with Codec Awareness

常见合作者