Kwang Moo Yi (@kwangmoo_yi)
2026-01-12 | ❤️ 62 | 🔁 7
Wu et al., “From Rays to Projections: Better Inputs for Feed-Forward View Synthesis”
Train a DiT to recover the full image from point cloud rasters. Is 3d “cueing” all we need? In similar spirit as other works that “fix” rough 3D renders. https://x.com/kwangmoo_yi/status/2010797805980532953/video/1
🔗 원본 링크
미디어
🔗 Related
Auto-generated - needs manual review