Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings

نویسندگان

چکیده

Dense prediction tasks are common for 3D point clouds, but the uncertainties inherent in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method dense clouds. Inspired by metric learning, key idea of CUE is to explore cross-point upon conventional pipeline. Specifically, involves building probabilistic embedding model then enforcing alignments space. We also propose CUE+, which enhances explicitly modeling dependencies covariance matrix. demonstrate that both CUE+ generic effective clouds with two different tasks: (1) geometric feature learning first time obtain well-calibrated uncertainty, (2) semantic segmentation reduce uncertainty's Expected Calibration Error state-of-the-arts 16.5%. All estimated without compromising predictive performance.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Tangent Convolutions for Dense Prediction in 3D

We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions – a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method operates directly on surface geometry. Crucially, the construction is applicable to unstructured point clouds and other noisy real-world data. We show that t...

متن کامل

Dense 3D Regression for Hand Pose Estimation

We present a simple and effective method for 3D hand pose estimation from a single depth frame. As opposed to previous state-of-the-art methods based on holistic 3D regression, our method works on dense pixel-wise estimation. This is achieved by careful design choices in pose parameterization, which leverages both 2D and 3D properties of depth map. Specifically, we decompose the pose parameters...

متن کامل

Uncertainty in 3D Shape Estimation

This paper analyses the uncertainty in the estimation of shape from different cues, specifically motion, stereo, and texture. It is shown that there are computational limitations of a statistical nature that previously have not been recognized. Because there is noise in all the input parameters, we cannot avoid bias. The analysis of shape from multiple views rests on a new constraint which rela...

متن کامل

Density estimation via cross-validation: Model selection point of view

The problem of model selection by cross-validation is addressed in the density estimation framework. Extensively used in practice, cross-validation (CV) remains poorly understood, especially in the non-asymptotic setting which is the main concern of this work. A recurrent problem with CV is the computation time it involves. This drawback is overcome here thanks to closed-form expressions for th...

متن کامل

Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in attempt to predict 3D shapes, where information is rich only on the surfaces. In this paper, we propose a novel 3D generative modeling framework to efficien...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE robotics and automation letters

سال: 2023

ISSN: ['2377-3766']

DOI: https://doi.org/10.1109/lra.2023.3256085