Marigold V2 tops NYUv2, KITTI, ETH3D, ScanNet and DIODE depth benchmarks
AntonObukhov1 · x · 2026-09-09
Marigold V2 results: all Marigold modalities — depth, surface normals, albedo — are simply better. On depth, it beats every model trained on comparable data across NYUv2, KITTI, ETH3D, ScanNet, and DIODE. Before/after sliders (RGB → V1.1 → V2) show clear gains on fur and thin details.
Related event: Marigold V2 Released: Single-GPU Fine-tuned DiT for Depth Estimation(5 posts)→
More from Research
- Lila Sciences cofounder Ben Kompa makes MIT TR35 list for autonomous science push — tw_killian · 2026-09-09
- 100 rule-based verifiers and 300 tasks: team builds a working RL recipe for video models — DanielKhashabi · 2026-09-09
- Researchers' 2022 paper warned privacy issues like this were coming — thegautamkamath · 2026-09-09
- Local Bad Behavior In RL Doesn't Produce Emergent Misalignment, Per Hacker-Opus — 1a3orn · 2026-09-09
- Speculative thread: capability-RL-trained LLMs may learn a 'use every affordance' heuristic — 1a3orn · 2026-09-09
- Pretraining progress is mostly from data: 12x compute gains from data vs 3.7x from models — sebkrier · 2026-09-09