Lapis: Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention
kwangmoo_yi · x · 2026-09-02
Liu et al. present Lapis, a method for depth estimation using pixel-space diffusion combined with linear attention. Contrary to the expectation that generative pixel-space methods are slow, the approach achieves SOTA results with speed comparable to DA3, thanks to the effectiveness of modern one-step denoisers.
Related event: Lapis Open-Sources Efficient Pixel-Space Diffusion Depth Estimation(2 posts)→
More from Multimodal
- AI-generated Snape strolling through a street crowd goes viral for its realism — paulinoow · 2026-10-18
- Luma shares filmmaking-style workflow: motion-capture real stunts then restyle with video-to-video — lmoroney · 2026-10-18
- MOSS-Image-SFT at 4 Steps Draws Hype: 320x320 to 2K Without Artifacts — Powerful_Evening5495 · 2026-10-18
- MOSS SFT vs Flux 3 Klein vs SD 3.0: Same-Prompt Comparison Exposes SD3's Age — ZootAllures9111 · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Omni 1'1 flash video demo generates atmospheric foggy Victorian haunted house — Dense-Instruction210 · 2026-10-18