↓Skip to main content

🏒 Nanjing University

StrandHead: Text to Strand-Disentangled 3D Head Avatars Using Hair Geometric Priors
·1741 words·9 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision 3D Vision 🏒 Nanjing University
’’ StrandHead: ν…μŠ€νŠΈλ§ŒμœΌλ‘œ 사싀적인 3D ν—€λ“œ 아바타와 μ„¬μ„Έν•œ ν—€μ–΄μŠ€νƒ€μΌκΉŒμ§€ 생성.''
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
·3493 words·17 mins· loading · loading
AI Generated πŸ€— Daily Papers Computer Vision Video Understanding 🏒 Nanjing University
InstanceCap: μΈμŠ€ν„΄μŠ€ 인식 ꡬ쑰화 μΊ‘μ…˜μ„ 톡해 ν…μŠ€νŠΈ-λΉ„λ””μ˜€ 생성을 κ°œμ„ ν•©λ‹ˆλ‹€.