lee

MarvinSOTA's activity

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

upvoted 4 papers 1 day ago

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 2 days ago • 36

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published 5 days ago • 149

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation

Paper • 2603.16669 • Published 4 days ago • 68

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

Paper • 2603.19231 • Published 2 days ago • 28

liked a dataset 5 days ago

ropedia-ai/xperience-10m

Updated 1 day ago • 4.03k • 115

upvoted a paper 26 days ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 26 days ago • 516

liked a Space 5 months ago

Running on Zero

Featured

227

MIDI 3D

📚

227

Image to Compositional 3D Scene Generation

upvoted a paper 5 months ago

Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting

Paper • 2508.01098 • Published Aug 1, 2025 • 1

liked a model 5 months ago

microsoft/TRELLIS-image-large

Image-to-3D • Updated Dec 6, 2024 • 3.65M • 630

upvoted a paper 7 months ago

STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

Paper • 2508.10893 • Published Aug 14, 2025 • 31

upvoted a paper 10 months ago

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published Jun 5, 2025 • 59

liked a dataset 10 months ago

3dlg-hcvc/s2o

Updated May 15, 2025 • 167 • 2

liked 2 Spaces 11 months ago

Running on Zero

Featured

253

MatchAnything

🏢

253

Match images to find similar pictures instantly

Running

10

Find3D

⚡

10

Find Anything in 3D: Open-World 3D Part Segmentation Model

liked a Space about 1 year ago

Runtime error

11

3DEnhancer

🔆

11

Use multi-view diffusion to enhance low-quality 3D assets