Chih-hai Su

ohinic's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics

Paper • 2610.19729 • Published 4 days ago • 17

authored 3 papers 2 days ago

Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion

Paper • 2610.18871 • Published 5 days ago • 31

LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

Paper • 2510.15868 • Published Oct 17, 2025 • 27

See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation

Paper • 2509.22653 • Published Sep 26, 2025 • 25

published a model 2 days ago

ohinic/cepheid

Updated 2 days ago • 5

updated a model 3 days ago

ohinic/cepheid

Updated 2 days ago • 5

liked 3 models 3 days ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 4.36M • • 6.19k

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 7.8M • • 17.9k

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 11 days ago • 158k • • 2.6k

upvoted a paper 4 days ago

Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion

Paper • 2610.18871 • Published 5 days ago • 31

upvoted a paper 9 days ago

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Paper • 2610.12461 • Published 10 days ago • 63

upvoted a paper 16 days ago

PROWBench: Do Video Models Render What the Program Specifies?

Paper • 2610.02205 • Published 13 days ago • 75

upvoted a paper about 1 month ago

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

Paper • 2609.04201 • Published Sep 3 • 50

upvoted 2 papers 12 months ago

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Paper • 2510.15869 • Published Oct 17, 2025 • 50

LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

Paper • 2510.15868 • Published Oct 17, 2025 • 27

upvoted a paper about 1 year ago

See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation

Paper • 2509.22653 • Published Sep 26, 2025 • 25

upvoted a paper over 1 year ago

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

Paper • 2502.05176 • Published Feb 7, 2025 • 40

upvoted 2 papers almost 2 years ago

SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes

Paper • 2410.17249 • Published Oct 22, 2024 • 44

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors

Paper • 2410.16271 • Published Oct 21, 2024 • 84

upvoted a paper about 2 years ago

BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes

Paper • 2407.15848 • Published Jul 22, 2024 • 17