Reconstructing the World in 3D: From Photosynth to NeRFs and IARPA's Next Bet
bilawalsidhu · x · 2026-08-13
This deep dive traces the evolution of 3D reconstruction from random internet photos.
- History: From Photosynth proving 3D reconstruction of smaller monuments in 2008, to "Building Rome in a Day" scaling it to entire cities in 2009.
- Tech Evolution: Covers the leap from early point clouds to modern NeRFs and 3D Gaussian Splatting, alongside key milestones like the Long Tail Problem, MegaDepth, and the Mannequin Challenge.
- Frontiers: Analyzes applications of MegaScenes, Doppelgangers, foundation models, and the breakthrough of MegaDepth-X.
- Future: Explains why IARPA is funding the next generation of this technology and looks ahead to the 4D frontier and the Sensorium.
More from Multimodal
- Suno Sparks User Backlash Over Sudden ToS Changes and Model Retirement — nptacek · 2026-08-13
- Image Generation Comparison: Grok vs. GPT-5.5 — Aizkmusic · 2026-08-13
- Advanced TTS Workflows: Injecting Emotional Depth into Cloned Voices — pol6oWu4 · 2026-08-13
- Krea2 Upscale Artifacts: Devs Discuss Multi-Pass Workflow Pitfalls and LoRA Conflicts — sadronmeldir · 2026-08-13
- Advanced MiniMax Video Generation: Prompting for Multi-Angle Location Consistency — MysteriousPepper8908 · 2026-08-13
- Workflow Breakdown: Creating a 3-Minute Anime Short Film Entirely with MiniMax — foxdit · 2026-08-13