NBS ditches cost volumes for a ViT, hitting SOTA stereo matching with faster inference
CSProfKGD · x · 2026-09-02
"NBS: No Bias Stereo" removes cost volumes, 3D convolutions, and iterative refinement from stereo matching. Instead it uses a simple ViT trained on massive synthetic data, achieving state-of-the-art accuracy with substantially faster inference.
Related event: NBS: Simple ViT Achieves SOTA Stereo Matching Without Cost Volumes(2 posts)→
More from Research
- NeoMME: From-Scratch Multimodal Encoders at 260M/800M With No Vision Tower — CShorten30 · 2026-09-03
- Do LLMs Have Research Taste? Lossfunk Paper Tests It via Future Direction Choice — paraschopra · 2026-09-03
- Action Chunking Boosts Contrastive RL Even in Fully Online RL, Study Finds — ben_eysenbach · 2026-09-03
- Coding models are running out of data — PL researchers propose 'intent computing' as the fix — LingmingZhang · 2026-09-03
- davidad Backs Call to Ban Naive RLVR: 'Everything Should Be Model-Graded' — davidad · 2026-09-03
- Computerphile Deep Dive: How Watermarks Track AI-Generated Content — Computerphile · 2026-09-03