Native Depth Estimation in Ultralytics: Absolute Distance from a Single RGB Image
MonaJalal_ · x · 2026-07-31
@ultralytics now natively supports depth estimation. The model outputs an absolute distance in meters for every pixel using just a single RGB image.
Key highlights:
- No extra hardware: Eliminates the need for stereo rigs or LiDAR, easily retrofittable to existing cameras.
- Lightweight & fast: Only 6.4M parameters, running 7.7× faster than Depth Anything V2.
- Offline: Capable of running completely offline.
Related event: Ultralytics YOLO Launches Native Monocular Depth Estimation(2 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16