VI3 anchors pretrained 3D foundation models to metric scale using only IMU readings
zhenjun_zhao · x · 2026-09-05
A model-agnostic framework from Javier Civera's group that metrically anchors pretrained 3D foundation models using only IMU readings. By preintegrating IMU data into a metric motion reference, VI3 recovers the scale of 3DFM outputs without ground-truth supervision, with adaptable anchoring strategies for different architectures. Experiments on synthetic and real aerial datasets show it preserves geometric consistency, acting as fine refinement under well-conditioned motion and a strong prior otherwise.
More from Research
- Metaⁿ and Recuris: filling the missing pieces in recursive self-improvement — TheTuringPost · 2026-09-05
- LLMs exploiting Lean bugs is a short-term problem, author argues — avt_im · 2026-09-05
- FinFIRST benchmark tests agents on real financial research: source discovery, evidence selection and math — alifcoder · 2026-09-05
- Valeo.ai Brings 5 ECCV 2026 Papers on Driving Video Prediction and LVLM Safety — abursuc · 2026-09-05
- Sakana AI's Percept-Lens: a simple rule on frozen vision features detects AI images — SakanaAILabs · 2026-09-05
- ZipMVS compresses cost volumes for memory-efficient multi-view stereo reconstruction — zhenjun_zhao · 2026-09-05