# RGB-D Local Implicit Function for Depth Completion of Transparent Objects

arXiv: https://arxiv.org/abs/2104.00622 · HTML: https://mlsanity.com/paper/2104.00622/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 1 Apr 2021.

## Builds on (most cited first, 30 of 38)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction](https://mlsanity.com/paper/1905.10711/) (2019)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Learning Shape Templates with Structured Implicit Functions](https://mlsanity.com/paper/1904.06447/) (2019)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [Single-Image Depth Perception in the Wild](https://mlsanity.com/paper/1604.03901/) (2016)
- [Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image](https://mlsanity.com/paper/1709.07492/) (2017)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Human Pose Estimation with Iterative Error Feedback](https://mlsanity.com/paper/1507.06550/) (2015)

## Built on by (most cited first, 30 of 64)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects](https://mlsanity.com/paper/2110.14217/) (2021)
- [Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification](https://mlsanity.com/paper/2203.10192/) (2022)
- [TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline](https://mlsanity.com/paper/2202.08471/) (2022)
- [Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects](https://mlsanity.com/paper/2208.03792/) (2022)
- [ClearPose: Large-scale Transparent Object Dataset and Benchmark](https://mlsanity.com/paper/2203.03890/) (2022)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects](https://mlsanity.com/paper/2110.00087/) (2021)
- [D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement](https://mlsanity.com/paper/2309.16118/) (2023)
- [StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS](https://mlsanity.com/paper/2211.01644/) (2022)
- [Transparent Shape from a Single View Polarization Image](https://mlsanity.com/paper/2204.06331/) (2022)
- [MVTrans: Multi-View Perception of Transparent Objects](https://mlsanity.com/paper/2302.11683/) (2023)
- [TransNet: Category-Level Transparent Object Pose Estimation](https://mlsanity.com/paper/2208.10002/) (2022)
- [TODE-Trans: Transparent Object Depth Estimation with Transformer](https://mlsanity.com/paper/2209.08455/) (2022)
- [FDCT: Fast Depth Completion for Transparent Objects](https://mlsanity.com/paper/2307.12274/) (2023)
- [LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow](https://mlsanity.com/paper/2409.05688/) (2024)
- [IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments](https://mlsanity.com/paper/2504.06827/) (2025)
- [Self-supervised Transparent Liquid Segmentation for Robotic Pouring](https://mlsanity.com/paper/2203.01538/) (2022)
- [TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation](https://mlsanity.com/paper/2502.07840/) (2025)
- [ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera](https://mlsanity.com/paper/2405.05648/) (2024)
- [ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulation](https://mlsanity.com/paper/2409.08926/) (2024)
- [Diffusion-Based Depth Inpainting for Transparent and Reflective Objects](https://mlsanity.com/paper/2410.08567/) (2024)
- [Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion](https://mlsanity.com/paper/2502.14616/) (2025)
- [Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation](https://mlsanity.com/paper/2503.11633/) (2025)
- [TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Image](https://mlsanity.com/paper/2503.12779/) (2025)
- [SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects](https://mlsanity.com/paper/2308.16528/) (2023)
- [RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation](https://mlsanity.com/paper/2311.12398/) (2023)
- [SuperCaustics: Real-time, open-source simulation of transparent objects for deep learning applications](https://mlsanity.com/paper/2107.11008/) (2021)
- [Visual-tactile Fusion for Transparent Object Grasping in Complex Backgrounds](https://mlsanity.com/paper/2211.16693/) (2022)
- [Virtual Occlusions Through Implicit Depth](https://mlsanity.com/paper/2305.07014/) (2023)

## Abstract (arXiv)

Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we introduce a new approach for depth completion of transparent objects from a single RGB-D image. Key to our approach is a local implicit neural representation built on ray-voxel pairs that allows our method to generalize to unseen objects and achieve fast inference speed. Based on this representation, we present a novel framework that can complete missing depth given noisy RGB-D input. We further improve the depth estimation iteratively using a self-correcting refinement model. To train the whole pipeline, we build a large scale synthetic dataset with transparent objects. Experiments demonstrate that our method performs significantly better than the current state-of-the-art methods on both synthetic and real world data. In addition, our approach improves the inference speed by a factor of 20 compared to the previous best method, ClearGrasp. Code and dataset will be released at https://research.nvidia.com/publication/2021-03_RGB-D-Local-Implicit.