# Test-Time Adaptation for Depth Completion

arXiv: https://arxiv.org/abs/2402.03312 · HTML: https://mlsanity.com/paper/2402.03312/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 63 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 48)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [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)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion](https://mlsanity.com/paper/1911.05377/) (2019)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [Binding Touch to Everything: Learning Unified Multimodal Tactile Representations](https://mlsanity.com/paper/2401.18084/) (2024)
- [CompletionFormer: Depth Completion with Convolutions and Vision Transformers](https://mlsanity.com/paper/2304.13030/) (2023)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [Sparse and noisy LiDAR completion with RGB guidance and uncertainty](https://mlsanity.com/paper/1902.05356/) (2019)
- [Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation](https://mlsanity.com/paper/1808.00769/) (2018)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [Learning Joint 2D-3D Representations for Depth Completion](https://mlsanity.com/paper/2012.12402/) (2020)
- [Dynamic Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2202.09769/) (2022)
- [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://mlsanity.com/paper/2207.11707/) (2022)

## Built on by (most cited first, 26 of 26)

- [WorDepth: Variational Language Prior for Monocular Depth Estimation](https://mlsanity.com/paper/2404.03635/) (2024)
- [OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration](https://mlsanity.com/paper/2411.19278/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions](https://mlsanity.com/paper/2410.02924/) (2024)
- [Distilling Monocular Foundation Model for Fine-grained Depth Completion](https://mlsanity.com/paper/2503.16970/) (2025)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens](https://mlsanity.com/paper/2508.04928/) (2025)
- [All-day Depth Completion](https://mlsanity.com/paper/2405.17315/) (2024)
- [IT3: Idempotent Test-Time Training](https://mlsanity.com/paper/2410.04201/) (2024)
- [Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior](https://mlsanity.com/paper/2502.06338/) (2025)
- [UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completion](https://mlsanity.com/paper/2410.18074/) (2024)
- [Progressive Test Time Energy Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2503.16616/) (2025)
- [Radar-Guided Polynomial Fitting for Metric Depth Estimation](https://mlsanity.com/paper/2503.17182/) (2025)
- [Test-Time Distillation for Continual Model Adaptation](https://mlsanity.com/paper/2506.02671/) (2025)
- [ETA: Energy-based Test-time Adaptation for Depth Completion](https://mlsanity.com/paper/2508.05989/) (2025)
- [DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image](https://mlsanity.com/paper/2504.01596/) (2025)
- [Depth Completion as Parameter-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2602.14751/) (2026)
- [StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion](https://mlsanity.com/paper/2603.01765/) (2026)
- [Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion](https://mlsanity.com/paper/2508.04984/) (2025)
- [Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency](https://mlsanity.com/paper/2603.09798/) (2026)
- [DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance](https://mlsanity.com/paper/2509.26498/) (2025)
- [VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Clouds](https://mlsanity.com/paper/2608.20740/) (2026)
- [ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting](https://mlsanity.com/paper/2512.17908/) (2025)
- [Test-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models](https://mlsanity.com/paper/2604.02009/) (2026)
- [From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation](https://mlsanity.com/paper/2608.27860/) (2026)
- [Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion](https://mlsanity.com/paper/2609.06007/) (2026)

## Abstract (arXiv)

It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require the source data on which the model was trained (often not available), while others, i.e., source-free DA, require many passes through the testing data. We propose an online test-time adaptation method for depth completion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the performance gap in a single pass. We first present a study on how the domain shift in each data modality affects model performance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image, we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e., adaptation layer) to align image and sparse depth features from the target test domain to that of the source domain. We evaluate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%.