TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Boosting Monocular Depth Estimation Models to High-Resolut...

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, Yağız Aksoy

2021-05-28CVPR 2021 1Depth EstimationMonocular Depth Estimation
PaperPDFCode(official)

Abstract

Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method builds on our analysis on how the input resolution and the scene structure affects depth estimation performance. We demonstrate that there is a trade-off between a consistent scene structure and the high-frequency details, and merge low- and high-resolution estimations to take advantage of this duality using a simple depth merging network. We present a double estimation method that improves the whole-image depth estimation and a patch selection method that adds local details to the final result. We demonstrate that by merging estimations at different resolutions with changing context, we can generate multi-megapixel depth maps with a high level of detail using a pre-trained model.

Results

TaskDatasetMetricValueModel
Depth EstimationIBims-1D3R0.3222Miangoleh et al. (SGR)
Depth EstimationIBims-1ORD0.3938Miangoleh et al. (SGR)
Depth EstimationIBims-1RMSE0.1598Miangoleh et al. (SGR)
Depth EstimationIBims-1δ1.250.639Miangoleh et al. (SGR)
Depth EstimationIBims-1D3R0.4671Miangoleh et al. (MiDaS)
Depth EstimationIBims-1ORD0.5538Miangoleh et al. (MiDaS)
Depth EstimationIBims-1RMSE0.1965Miangoleh et al. (MiDaS)
Depth EstimationIBims-1δ1.250.746Miangoleh et al. (MiDaS)
Depth EstimationMiddlebury 2014D3R0.1578Miangoleh et al. (MiDaS)
Depth EstimationMiddlebury 2014ORD 0.3467Miangoleh et al. (MiDaS)
Depth EstimationMiddlebury 2014RMSE0.1557Miangoleh et al. (MiDaS)
Depth EstimationMiddlebury 2014δ1.250.7406Miangoleh et al. (MiDaS)
Depth EstimationMiddlebury 2014D3R0.2324Miangoleh et al. (SGR)
Depth EstimationMiddlebury 2014ORD 0.3879Miangoleh et al. (SGR)
Depth EstimationMiddlebury 2014RMSE0.1973Miangoleh et al. (SGR)
Depth EstimationMiddlebury 2014δ1.250.7891Miangoleh et al. (SGR)
3DIBims-1D3R0.3222Miangoleh et al. (SGR)
3DIBims-1ORD0.3938Miangoleh et al. (SGR)
3DIBims-1RMSE0.1598Miangoleh et al. (SGR)
3DIBims-1δ1.250.639Miangoleh et al. (SGR)
3DIBims-1D3R0.4671Miangoleh et al. (MiDaS)
3DIBims-1ORD0.5538Miangoleh et al. (MiDaS)
3DIBims-1RMSE0.1965Miangoleh et al. (MiDaS)
3DIBims-1δ1.250.746Miangoleh et al. (MiDaS)
3DMiddlebury 2014D3R0.1578Miangoleh et al. (MiDaS)
3DMiddlebury 2014ORD 0.3467Miangoleh et al. (MiDaS)
3DMiddlebury 2014RMSE0.1557Miangoleh et al. (MiDaS)
3DMiddlebury 2014δ1.250.7406Miangoleh et al. (MiDaS)
3DMiddlebury 2014D3R0.2324Miangoleh et al. (SGR)
3DMiddlebury 2014ORD 0.3879Miangoleh et al. (SGR)
3DMiddlebury 2014RMSE0.1973Miangoleh et al. (SGR)
3DMiddlebury 2014δ1.250.7891Miangoleh et al. (SGR)

Related Papers

$S^2M^2$: Scalable Stereo Matching Model for Reliable Depth Estimation2025-07-17$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning2025-07-17Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation2025-07-16Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network2025-07-15Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation2025-07-15Cameras as Relative Positional Encoding2025-07-14ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way2025-07-11