Depth Completion

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

9 leaderboard tables shown for this task, 9 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 96 papers with code (242 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation
  17 Oct 2016 4 repositories listed
  Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.
• PENet: Towards Precise and Efficient Image Guided Depth Completion
  1 Mar 2021 3 repositories listed
  More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map.
• Indoor Depth Completion with Boundary Consistency and Self-Attention
  22 Aug 2019 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced.
• Noise-Aware Unsupervised Deep Lidar-Stereo Fusion
  8 Apr 2019 3 repositories listed
  In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps.
• CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagation
  7 Nov 2024 2 repositories listed
  Previous methods fail to propagate depth features from the zone area to the outside-zone area effectively, thus suffering from degraded depth completion performance outside the zone.
• A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Driving
  29 Jan 2024 2 repositories listed
  Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction.
• Revisiting Deformable Convolution for Depth Completion
  3 Aug 2023 2 repositories listed
  Our study reveals that, different from prior work, deformable convolution needs to be applied on an estimated depth map with a relatively high density for better performance.
• Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
  20 Sep 2021 2 repositories listed Syntology ran 4 of 15 samples · 11 unverified
  Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to predict initial depth maps.
• Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation
  17 Jan 2020 2 repositories listed
  In this paper, we propose a depth completion and uncertainty estimation approach that better handles the challenges of aerial platforms, such as large viewpoint and depth variations, and limited computing resources.
• Learning Guided Convolutional Network for Depth Completion
  3 Aug 2019 2 repositories listed
  It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion.
• Unsupervised Depth Completion from Visual Inertial Odometry
  15 May 2019 2 repositories listed
  Our method first constructs a piecewise planar scaffolding of the scene, and then uses it to infer dense depth using the image along with the sparse points.
• Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera
  1 Jul 2018 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving.
• In Defense of Classical Image Processing: Fast Depth Completion on the CPU
  31 Jan 2018 2 repositories listed
  With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms.
• PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency
  10 Jul 2025 1 repository listed
  This paper presents PacGDC, a label-efficient technique that enhances data diversity with minimal annotation effort for generalizable depth completion.
• DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
  2 Apr 2025 1 repository listed
  To address these challenges, we propose a novel completion-based method, named DEPTHOR, featuring advances in both the training strategy and model architecture.
• Vanishing Depth: A Depth Adapter with Positional Depth Encoding for Generalized Image Encoders
  25 Mar 2025 1 repository listed
  Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support.
• SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
  3 Mar 2025 1 repository listed Syntology ran 2 of 14 samples · 12 unverified
  However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy.
• TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
  11 Feb 2025 1 repository listed
  Transparent object manipulation remains a sig- nificant challenge in robotics due to the difficulty of acquiring accurate and dense depth measurements.
• TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network
  19 Dec 2024 1 repository listed
  The sensing and manipulation of transparent objects present a critical challenge in industrial and laboratory robotics.
• OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration
  28 Nov 2024 1 repository listed
  To evaluate our model, we establish a new evaluation protocol named Robust-DC for zero-shot testing under various sparse depth patterns.
• Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
  27 Nov 2024 1 repository listed
  To address this, we introduce necessary adaptations to stereo models, leading to improved performance.
• Scale Propagation Network for Generalizable Depth Completion
  24 Oct 2024 1 repository listed
  Although deep learning based methods have made tremendous progress in this problem, these models cannot generalize well across different scenes that are unobserved in training, posing a fundamental limitation that yet…
• SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps
  16 Sep 2024 1 repository listed
  Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth…
• SDformer: Efficient End-to-End Transformer for Depth Completion
  12 Sep 2024 1 repository listed
  The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module.
• OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
  17 Jun 2024 1 repository listed Syntology ran 9 of 11 samples · 2 unverified
  Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs.
• A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion
  14 Jun 2024 1 repository listed
  Compared to the existing methods, our proposed network, achieves the state-of-the-art performance on the Matterport3D dataset.
• Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
  30 Apr 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  The main function of depth completion is to compensate for an insufficient and unpredictable number of sparse depth measurements of hardware sensors.
• RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion
  14 Apr 2024 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  Accurate completion and denoising of roof height maps are crucial to reconstructing high-quality 3D buildings.
• NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
  29 Mar 2024 1 repository listed
  Second, the occupancy scene representation is replaced with Signed Distance Field (SDF) hierarchical scene representation for high-quality reconstruction and view synthesis.
• Bilateral Propagation Network for Depth Completion
  17 Mar 2024 1 repository listed Syntology ran 1 of 6 samples · 5 unverified
  Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image.

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.