Chih-hai Su

ohinic's activity

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

upvoted 2 papers 1 day ago

Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning

Paper • 2610.26851 • Published 3 days ago • 26

InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation

Paper • 2610.26853 • Published 3 days ago • 26

upvoted a paper 3 days ago

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

Paper • 2610.18871 • Published 9 days ago • 33

upvoted a paper 5 days ago

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

Paper • 2610.19729 • Published 8 days ago • 19

upvoted a paper 12 days ago

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

Paper • 2610.12461 • Published 14 days ago • 66

upvoted a paper 19 days ago

PROWBench: Do Video Models Render What the Program Specifies?

Paper • 2610.02205 • Published 17 days ago • 75

upvoted a paper about 2 months ago

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

Paper • 2609.04201 • Published Sep 3 • 50

upvoted 3 papers about 1 year 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

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 • 45

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

upvoted 4 papers over 2 years ago

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

Paper • 2407.01519 • Published Jul 1, 2024 • 26

Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation

Paper • 2406.12849 • Published Jun 18, 2024 • 50

NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

Paper • 2406.06523 • Published Jun 10, 2024 • 53

Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields

Paper • 2402.13252 • Published Feb 20, 2024 • 19