MaSS makes self-supervised depth estimation scalable via scene structure
Tongji · hf · 2026-10-20
The MaSS framework improves self-supervised monocular depth estimation by separating structural representations from contextual features and adding a scene-structure discrimination objective, enabling scalable mixed-domain training and strong zero-shot generalization across diverse scenes.
More from Research
- DiverseUMI-100 open-sourced: 12k tasks from a 1M+ task dataset scaled in 8 weeks — k7agar · 2026-10-20
- Tsinghua's MGFlow hits one-step SOTA: FDr6 cut 23-38% on ImageNet, extends to streaming video — jiqizhixin · 2026-10-20
- Kimi K3 excels on new Frontier Code v1.1 bench but flops on Terminal Bench v4 — Ok_Warning2146 · 2026-10-20
- How activating a single neuron turns a model into an owl: interpretability deep-dive — Sauers_ · 2026-10-20
- EC2-Bench: Systematic Analysis of Edge-Cloud Collaboration for Long-Horizon LLM Agents — NortheasternUniversity1923 · 2026-10-20
- World Model Interpretability: From Decoding Representations to Understanding Latent Worlds — Jize Wang · 2026-10-20