Data to 14 Oct 2026

Sparsity Invariant CNNs

arXiv 1708.06500 ↗First posted 22 Aug 2017cs.CVcited by 326

Not on the map. Why?

Abstract (arXiv)

In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data. First, we show that traditional convolutional networks perform poorly when applied to sparse data even when the location of missing data is provided to the network. To overcome this problem, we propose a simple yet effective sparse convolution layer which explicitly considers the location of missing data during the convolution operation. We demonstrate the benefits of the proposed network architecture in synthetic and real experiments with respect to various baseline approaches. Compared to dense baselines, the proposed sparse convolution network generalizes well to novel datasets and is invariant to the level of sparsity in the data. For our evaluation, we derive a novel dataset from the KITTI benchmark, comprising 93k depth annotated RGB images. Our dataset allows for training and evaluating depth upsampling and depth prediction techniques in challenging real-world settings and will be made available upon publication.

Key facts. Cited by 326 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 68; 2022: 70; 2023: 60; 2024: 57; 2025: 37; 2026: 34.

326 papers.

Sort:

By area:

2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
2021Multimodal Virtual Point 3D Detectioncited by 166
2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 152
2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 121
2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 118

38 more

2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 101
2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 93
2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
2023Point Cloud Forecasting as a Proxy for 4D Occupancy Forecastingcited by 78
2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 78
2022Dynamic Spatial Propagation Network for Depth Completioncited by 71
2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
2024Bilateral Propagation Network for Depth Completioncited by 60
2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
2021OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Drivingcited by 57
2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 54
2021Radar-Camera Pixel Depth Association for Depth Completioncited by 50
2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 50
2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 49
2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 49
2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
2023OmniVec: Learning robust representations with cross modal sharingcited by 44
2026Image Generators are Generalist Vision Learnerscited by 43
2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
2024Tri-Perspective View Decomposition for Geometry-Aware Depth Completioncited by 42
2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
2021Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completioncited by 39
2022Achieving Risk Control in Online Learning Settingscited by 39
2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 39
2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
2023Exploiting Diffusion Prior for Generalizable Dense Predictioncited by 38
2022RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimationcited by 36
2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
2021PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Losscited by 31
2023FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimatorscited by 31

50 most cited of 326 All 326 (JSON)