NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinement
6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch during onboarding and have long trailed their model-based counterparts.
ProofPaper ↗
Key points
- We present NovaSplat, a model-free pipeline that closes this gap.
- From a short smartphone video captured at onboarding, we train a 3D Gaussian Splatting (3DGS) model that serves both as a template source for detection and coarse pose estimation and as a differentiable backbone for pose refinement.
- Our refiner optimizes the object-to-camera pose with combined photometric and geometric losses under a continuous rotation parametrization free of gradient singularities.
- We further introduce NovaSplat-Lite, an inference variant that is $3.1\times$ faster at negligible accuracy cost.
Sources (1)
- [1]NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and RefinementarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 09:54 AM
6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch during onboarding and have long trailed their model-based counterparts.
We present NovaSplat, a model-free pipeline that closes this gap.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
- Oct 8, 2026openai/codex rust-v0.162.0: 0.162.0
- Oct 8, 2026Microsoft Joins the Local AI Push
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing