← Authors

Jiahui Huang

21 papers · 2019–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (30) 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (6) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge πŸ”¬ Deep Specialist (10) ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (82) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (21)

Conferences

CVPR (9) ECCV (5) ICCV (3) ICLR (3) NIPS (1)

Top co-authors

Sanja Fidler (6) Shi-min Hu (6) Seungryong Kim (4) Francis Williams (4) Seokju Cho (4) Xuanchi Ren (4) Joon-Young Lee (4) Jiawei Yang (3) Or Litany (3) Yifan Lu (3)

Keywords

3d vision (4) point cloud (3) 3d reconstruction (3) diffusion model (3) motion estimation (3) depth estimation (3) autonomous driving (2) object tracking (2) video generation (2) surface reconstruction (2) point tracking (2) point cloud registration (1) sparse representation (1) probabilistic modeling (1) self-supervised learning (1) stereo vision (1) gaussian splatting (1) scene reconstruction (1) video understanding (1) monocular depth estimation (1)

Papers

OmniRe: Omni Urban Scene Reconstruction ICLR 2025
Seurat: From Moving Points to Depth CVPR 2025
Exploring Temporally-Aware Features for Point Tracking CVPR 2025
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models ICCV 2025
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control CVPR 2025
STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes ICLR 2025
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats NIPS 2024
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies CVPR 2024
FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking CVPR 2024
Local All-Pair Correspondence for Point Tracking ECCV 2024
Approximately Piecewise E(3) Equivariant Point Networks ICLR 2024
Neural Kernel Surface Reconstruction CVPR 2023
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion ICCV 2023
Dynamic 3D Scene Analysis by Point Cloud Accumulation ECCV 2022
Layered Controllable Video Generation ECCV 2022
CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-Scale Indoor Scene ECCV 2022
DI-Fusion: Online Implicit 3D Reconstruction With Deep Priors CVPR 2021
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization CVPR 2021
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings CVPR 2020
Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning ECCV 2020
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation ICCV 2019