Skip to content
conftrace_

Kaiwen Guo

16 papers · 2015–2026 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+7 more ↓ ๐Ÿ—บ๏ธ Taxonomy Completionist (34) ๐Ÿƒ Academic Marathon ยท Half ๐ŸŒ Conference Polyglot ยท Silver ๐ŸŒ‰ Interdisciplinary Bridge ยท Silver ๐Ÿฃ Hot Topic Early Bird
๐Ÿ‘ฅ Mega-Team ยท Legion ๐Ÿ† Keyword Champion (3) ๐ŸŒˆ Renaissance Researcher (6) ๐Ÿ”ฅ Unstoppable ยท Bronze ๐Ÿš€ Conference Pioneer ๐Ÿ’Ž Century Club ยท Bronze ๐Ÿ—ƒ๏ธ Keyword Collector (85)

Venues

CVPR (7) ECCV (3) ICCV (2) AAAI (1) ACL (1) IJCNLP (1) NeurIPS (1)

Top co-authors

Yebin Liu (8) Tao Yu (6) Qionghai Dai (5) Zerong Zheng (4) Feng Xu (3) Yuan Dong (3) Melissa Schoeller (2) Michael Zollhรถfer (2) Rohan Joshi (2) Lucas Evans (2)

Research topics

Computer Vision (10) Analysis (10) Deep Learning (7) Machine Learning (4) Domain-Specific (4) Generation (4) Models (4) Artificial Intelligence (3) Core AI (3) Learning Types (3) Computer Science (2) Application Areas (2) Applications (2) Architectures (2) Mathematics & Optimization (1)

Keywords

3d reconstruction (6) photorealistic rendering (3) depth sensor (3) human pose estimation (2) motion tracking (2) neural rendering (2) surface reconstruction (2) volumetric capture (2) knowledge distillation (1) human-object interaction (1) pose estimation (1) multi-task learning (1) question generation (1) feature embedding (1) 3d vision (1) iterative optimization (1) dense correspondence (1) motion capture (1) optical flow (1) face recognition (1)

Papers

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models ACL 2026 MAJI: A Multi-Agent Workflow for Augmenting Journalistic Interviews IJCNLP 2025 Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars NeurIPS 2024 URHand: Universal Relightable Hands CVPR 2024 Grouped Knowledge Distillation for Deep Face Recognition AAAI 2023 Geometry-Aware Single-Image Full-Body Human Relighting ECCV 2022 NeuralHOFusion: Neural Volumetric Rendering Under Human-Object Interactions CVPR 2022 Function4D: Real-Time Human Volumetric Capture From Very Sparse Consumer RGBD Sensors CVPR 2021 HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences CVPR 2021 NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering Using RGB Cameras CVPR 2021 POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture CVPR 2021 DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs ECCV 2018 DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor CVPR 2018 HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs ECCV 2018 BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera ICCV 2017 Robust Non-Rigid Motion Tracking and Surface Reconstruction Using L0 Regularization ICCV 2015