# Estimating Object Physical Properties from RGB-D Vision and Depth Robot Sensors Using Deep Learning

arXiv: https://arxiv.org/abs/2507.05029 · HTML: https://mlsanity.com/paper/2507.05029/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://mlsanity.com/paper/2201.07436/) (2022)
- [Estimation and Exploitation of Objects' Inertial Parameters in Robotic Grasping and Manipulation: A Survey](https://mlsanity.com/paper/1911.04397/) (2019)

## Built on by (most cited first, 2 of 2)

- [Physically Guided Visual Mass Estimation from a Single RGB Image](https://mlsanity.com/paper/2601.20303/) (2026)
- [Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations](https://mlsanity.com/paper/2607.07962/) (2026)

## Abstract (arXiv)

Inertial mass plays a crucial role in robotic applications such as object grasping, manipulation, and simulation, providing a strong prior for planning and control. Accurately estimating an object's mass before interaction can significantly enhance the performance of various robotic tasks. However, mass estimation using only vision sensors is a relatively underexplored area. This paper proposes a novel approach combining sparse point-cloud data from depth images with RGB images to estimate the mass of objects. We evaluate a range of point-cloud processing architectures, alongside RGB-only methods. To overcome the limited availability of training data, we create a synthetic dataset using ShapeNetSem 3D models, simulating RGBD images via a Kinect camera. This synthetic data is used to train an image generation model for estimating dense depth maps, which we then use to augment an existing dataset of images paired with mass values. Our approach significantly outperforms existing benchmarks across all evaluated metrics. The data generation (https://github.com/RavineWindteer/ShapenetSem-to-RGBD) as well as the training of the depth estimator (https://github.com/RavineWindteer/GLPDepth-Edited) and the mass estimator (https://github.com/RavineWindteer/Depth-mass-estimator) are available online.