# EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images

arXiv: https://arxiv.org/abs/2503.04441 · HTML: https://mlsanity.com/paper/2503.04441/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks](https://mlsanity.com/paper/2002.10118/) (2020)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning](https://mlsanity.com/paper/1611.03631/) (2016)
- [Revealing the Dark Secrets of Masked Image Modeling](https://mlsanity.com/paper/2205.13543/) (2022)
- [BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration](https://mlsanity.com/paper/1604.01093/) (2016)
- [Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery](https://mlsanity.com/paper/1903.00268/) (2019)
- [Do Bayesian Neural Networks Need To Be Fully Stochastic?](https://mlsanity.com/paper/2211.06291/) (2022)
- [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://mlsanity.com/paper/2201.07436/) (2022)
- [Robust Monocular Depth Estimation under Challenging Conditions](https://mlsanity.com/paper/2308.09711/) (2023)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Panoptic Multi-TSDFs: a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency](https://mlsanity.com/paper/2109.10165/) (2021)
- [Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping](https://mlsanity.com/paper/1909.04631/) (2019)
- [Meaningful Maps With Object-Oriented Semantic Mapping](https://mlsanity.com/paper/1609.07849/) (2016)
- [SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images](https://mlsanity.com/paper/2403.10662/) (2024)
- [NBV-SC: Next Best View Planning based on Shape Completion for Fruit Mapping and Reconstruction](https://mlsanity.com/paper/2209.15376/) (2022)
- [Robust Fusion for Bayesian Semantic Mapping](https://mlsanity.com/paper/2303.07836/) (2023)

## Built on by (most cited first, 3 of 3)

- [Privacy-Preserving Semantic Segmentation from Ultra-Low-Resolution RGB Inputs](https://mlsanity.com/paper/2507.16034/) (2025)
- [UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene](https://mlsanity.com/paper/2510.06754/) (2025)
- [Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2610.15854/) (2026)

## Abstract (arXiv)

For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer from overconfident semantic predictions, and sparse and noisy depth sensing, leading to inconsistent map representations. In this paper, we therefore introduce EvidMTL, a multi-task learning framework that uses evidential heads for depth estimation and semantic segmentation, enabling uncertainty-aware inference from monocular RGB images. To enable uncertainty-calibrated evidential multi-task learning, we propose a novel evidential depth loss function that jointly optimizes the belief strength of the depth prediction in conjunction with evidential segmentation loss. Building on this, we present EvidKimera, an uncertainty-aware semantic surface mapping framework, which uses evidential depth and semantics prediction for improved 3D metric-semantic consistency. We train and evaluate EvidMTL on the NYUDepthV2 and assess its zero-shot performance on ScanNetV2, demonstrating superior uncertainty estimation compared to conventional approaches while maintaining comparable depth estimation and semantic segmentation. In zero-shot mapping tests on ScanNetV2, EvidKimera outperforms Kimera in semantic surface mapping accuracy and consistency, highlighting the benefits of uncertainty-aware mapping and underscoring its potential for real-world robotic applications.