paper-with-me

Papers

UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration

2022-08-04 · Zhilei Chen, Honghua Chen, Lina Gong, Xuefeng Yan, Jun Wang, Yanwen Guo, Jing Qin, Mingqiang Wei

High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and non-overlapping regions, which has always been neglected and significantly affects the registration performance. Beyond the current wisdom, we propose a novel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tackle the ambiguous overlap prediction problem; to our knowledge, this is the first to explicitly introduce overlap uncertainty to point cloud registration. Moreover, we induce the feature extractor to implicitly perceive the shape knowledge through a completion decoder, and present a geometric relation embedding for Transformer to obtain transformation-invariant geometry-aware feature representations. With the merits of more reliable overlap scores and more precise dense correspondences, UTOPIC can achieve stable and accurate registration results, even for the inputs with limited overlapping areas. Extensive quantitative and qualitative experiments on synthetic and real benchmarks demonstrate the superiority of our approach over state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2208.02712

Code (1)

zhileichen99/utopic 공식 구현 pytorch

Tasks

DecoderPoint Cloud RegistrationPrediction

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

To Predict or to Reject: Causal Effect Estimation with Uncertainty on Networked Data

2023-09-15 · Hechuan Wen, Tong Chen, Li Kheng Chai, Shazia Sadiq 외

Due to the imbalanced nature of networked observational data, the causal effect predictions for some individuals can severely violate the positivity/overlap assumption, rendering unreliable estimations. Nevertheless, thi…

Decision-Aware Uncertainty Evaluation of Vision-Language Model-Based Early Action Anticipation for Human-Robot Interaction

2026-03-09 · Zhaoda Du, Michael Bowman, Qiaojie Zheng, Xiaoli Zhang arxiv

Robots in shared workspaces must interpret human actions from partial, ambiguous observations, where overconfident early predictions can lead to unsafe or disruptive interaction. This challenge is amplified in egocentric…

Action AnticipationAction Recognition

Predicting the impact of treatments over time with uncertainty aware neural differential equations

2022-02-24 · Edward De Brouwer, Javier González Hernández, Stephanie Hyland

Predicting the impact of treatments from observational data only still represents a majorchallenge despite recent significant advances in time series modeling. Treatment assignments are usually correlated with the predic…

Causal InferencecounterfactualTime SeriesTime Series Analysis

Interval-Based AUC (iAUC): Extending ROC Analysis to Uncertainty-Aware Classification

2026-02-04 · Yuqi Li, Matthew M. Engelhard arxiv

In high-stakes risk prediction, quantifying uncertainty through interval-valued predictions is essential for reliable decision-making. However, standard evaluation tools like the receiver operating characteristic (ROC) c…

An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions

2021-10-07 · Afshar Shamsi, Hamzeh Asgharnezhad, AmirReza Tajally, Saeid Nahavandi 외

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have be…

Deep LearningUncertainty Quantification