Mingwei Li

Longxiang-ai's activity

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

authored 4 papers 3 days ago

TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors

Paper • 2504.12799 • Published Aug 3, 2025

TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Paper • 2602.00839 • Published Jan 31 • 2

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Paper • 2511.19268 • Published Nov 24, 2025 • 1

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Paper • 2312.15258 • Published Dec 23, 2023 • 12

liked a model 3 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 6 days ago • 837k • • 9.6k

upvoted 2 papers 3 days ago

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Paper • 2312.15258 • Published Dec 23, 2023 • 12

TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation

Paper • 2602.00839 • Published Jan 31 • 2

liked a dataset about 2 months ago

FudanCVL/EffectErase

Viewer • Updated Jun 27 • 797k • 514 • 20

updated a Space about 2 months ago

Sleeping

Agents

TransNormal-2 Demo

🚀

Generate camera-space normal maps from photos

published a Space about 2 months ago

Sleeping

Agents

TransNormal-2 Demo

🚀

Generate camera-space normal maps from photos

upvoted 2 papers about 2 months ago

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

Paper • 2606.12303 • Published Jun 10 • 32

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

Paper • 2606.12243 • Published Jun 10 • 36

updated a dataset 2 months ago

Longxiang-ai/TransNormal-Synthetic

Viewer • Updated May 22 • 3.61k • 31 • 2

updated a model 2 months ago

Longxiang-ai/TransNormal

Image-to-Image • 0.9B • Updated May 22 • 7 • 1

liked a dataset 2 months ago

Longxiang-ai/TransLab

Viewer • Updated Mar 14 • 7.7k • 942 • 1

liked a model 2 months ago

Longxiang-ai/TransNormal

Image-to-Image • 0.9B • Updated May 22 • 7 • 1

upvoted a paper 4 months ago

RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details

Paper • 2604.06870 • Published Apr 8 • 44

liked a Space 4 months ago

Running on Zero

Agents

38

RefineAnything

🖼

38

Refine selected image area with a text prompt

liked a model 5 months ago

Qwen/Qwen3.5-9B

Image-Text-to-Text • 10B • Updated Mar 2 • 12.1M • • 1.78k

updated a dataset 5 months ago

Longxiang-ai/TransLab

Viewer • Updated Mar 14 • 7.7k • 942 • 1