Methods › SPEED
SPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
SPEED
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene understanding and visual odometry, which are key components in autonomous and robotic systems. Approaches based on the state of the art vision transformer architectures are extremely deep and complex not suitable for real-time inference operations on edge and autonomous systems equipped with low resources (i.e. robot indoor navigation and surveillance). This paper presents SPEED, a Separable Pyramidal pooling EncodEr-Decoder architecture designed to achieve real-time frequency performances on multiple hardware platforms. The proposed model is a fast-throughput deep architecture for MDE able to obtain depth estimations with high accuracy from low resolution images using minimum hardware resources (i.e. edge devices). Our encoder-decoder model exploits two depthwise separable pyramidal pooling layers, which allow to increase the inference frequency while reducing the overall computational complexity. The proposed method performs better than other fast-throughput architectures in terms of both accuracy and frame rates, achieving real-time performances over cloud CPU, TPU and the NVIDIA Jetson TX1 on two indoor benchmarks: the NYU Depth v2 and the DIML Kinect v2 datasets.
In Syntology repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2310.12072) is about this method is not checked.
Origin paper of this answer, arXiv:2310.12072 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 9,576 · with a code link: 3,061 · where Syntology ran a sample: 779 (655 with a run with no instrument failure, 124 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (779 of 9,576 tagged: 655 with a run with no instrument failure, 124 where every run was a failure of Syntology's instrument)
Page 1 of 96: papers 1 to 100 of 9,573, newest first by the archive's date (ties by slug), in archive order.
3 tagged papers are not listed: the archive title is spam (see /not-shown).
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker 16 Jul 2025 · 1 repository · arXiv:2507.12378
-
COLI: A Hierarchical Efficient Compressor for Large Images 15 Jul 2025 · 0 repositories · arXiv:2507.11443
-
Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection 15 Jul 2025 · 1 repository · arXiv:2507.11136
-
Neurosymbolic Reasoning Shortcuts under the Independence Assumption 15 Jul 2025 · 1 repository · arXiv:2507.11357Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Streaming 4D Visual Geometry Transformer 15 Jul 2025 · 1 repository · arXiv:2507.11539Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping 15 Jul 2025 · 0 repositories · arXiv:2507.11279
-
Federated Learning with Graph-Based Aggregation for Traffic Forecasting 13 Jul 2025 · 0 repositories · arXiv:2507.09805
-
Lizard: An Efficient Linearization Framework for Large Language Models 11 Jul 2025 · 0 repositories · arXiv:2507.09025
-
GNN-CNN: An Efficient Hybrid Model of Convolutional and Graph Neural Networks for Text Representation 10 Jul 2025 · 1 repository · arXiv:2507.07414
-
GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field 8 Jul 2025 · 0 repositories · arXiv:2507.05594
-
Hyperspectral Anomaly Detection Methods: A Survey and Comparative Study 8 Jul 2025 · 0 repositories · arXiv:2507.05730
-
Robust One-step Speech Enhancement via Consistency Distillation 8 Jul 2025 · 1 repository · arXiv:2507.05688
-
Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures 7 Jul 2025 · 0 repositories · arXiv:2507.10446
-
MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection 6 Jul 2025 · 1 repository · arXiv:2507.04369Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)
-
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference 5 Jul 2025 · 0 repositories · arXiv:2507.03865
-
Hita: Holistic Tokenizer for Autoregressive Image Generation 3 Jul 2025 · 0 repositories · arXiv:2507.02358Syntology 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 11 harvested samples)
-
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation 29 Jun 2025 · 1 repository · arXiv:2506.23347
-
Deterministic Object Pose Confidence Region Estimation 28 Jun 2025 · 0 repositories · arXiv:2506.22720
-
BitMark for Infinity: Watermarking Bitwise Autoregressive Image Generative Models 26 Jun 2025 · 0 repositories · arXiv:2506.21209Syntology 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples)
-
CaloHadronic: a diffusion model for the generation of hadronic showers 26 Jun 2025 · 1 repository · arXiv:2506.21720
-
Detection of Breast Cancer Lumpectomy Margin with SAM-incorporated Forward-Forward Contrastive Learning 26 Jun 2025 · 1 repository · arXiv:2506.21006
-
DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster 26 Jun 2025 · 0 repositories · arXiv:2506.21263
-
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching 26 Jun 2025 · 1 repository · arXiv:2506.21091
-
Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning 26 Jun 2025 · 0 repositories · arXiv:2506.21427Syntology 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation 26 Jun 2025 · 0 repositories · arXiv:2506.21022
-
Integrating Vehicle Acoustic Data for Enhanced Urban Traffic Management: A Study on Speed Classification in Suzhou 26 Jun 2025 · 0 repositories · arXiv:2506.21269
-
SAM4D: Segment Anything in Camera and LiDAR Streams 26 Jun 2025 · 0 repositories · arXiv:2506.21547
-
Collaborative Batch Size Optimization for Federated Learning 25 Jun 2025 · 0 repositories · arXiv:2506.20511
-
Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices 25 Jun 2025 · 0 repositories · arXiv:2506.20644
-
Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking 25 Jun 2025 · 1 repository · arXiv:2506.20381
-
Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents 24 Jun 2025 · 0 repositories · arXiv:2506.20062
-
Extreme Learning Machines for Exoplanet Simulations: A Faster, Lightweight Alternative to Deep Learning 24 Jun 2025 · 0 repositories · arXiv:2506.19679
-
GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computing 24 Jun 2025 · 1 repository · arXiv:2506.19224
-
MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection 24 Jun 2025 · 0 repositories · arXiv:2506.19884
-
Orthogonal Soft Pruning for Efficient Class Unlearning 24 Jun 2025 · 0 repositories · arXiv:2506.19891
-
Virtual Memory for 3D Gaussian Splatting 24 Jun 2025 · 0 repositories · arXiv:2506.19415
-
2D Triangle Splatting for Direct Differentiable Mesh Training 23 Jun 2025 · 0 repositories · arXiv:2506.18575
-
Achieving 70 Gb/s Over A VCSEL-Based Optical Wireless Link Using A Multi-Mode Fiber-Coupled Receiver 23 Jun 2025 · 0 repositories · arXiv:2506.18864
-
ARSAR-Net: Intelligent SAR Imaging with Adaptive Regularization 23 Jun 2025 · 0 repositories · arXiv:2506.18324
-
Let Your Video Listen to Your Music! 23 Jun 2025 · 0 repositories · arXiv:2506.18881
-
Lightweight RGB-T Tracking with Mobile Vision Transformers 23 Jun 2025 · 0 repositories · arXiv:2506.19154
-
Physics-Informed Neural Networks for Nonlocal Flow Modeling of Connected Automated Vehicles 23 Jun 2025 · 0 repositories · arXiv:2506.18357
-
Simulation of a closed-loop dc-dc converter using a physics-informed neural network-based model 23 Jun 2025 · 0 repositories · arXiv:2506.19178
-
SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction 23 Jun 2025 · 0 repositories · arXiv:2506.19139
-
Non-Euclidean Enriched Contraction Theory for Monotone Operators and Monotone Dynamical Systems 22 Jun 2025 · 0 repositories · arXiv:2506.17990
-
TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs 22 Jun 2025 · 0 repositories · arXiv:2506.17894
-
H-QuEST: Accelerating Query-by-Example Spoken Term Detection with Hierarchical Indexing 20 Jun 2025 · 0 repositories · arXiv:2506.16751
-
Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments 20 Jun 2025 · 0 repositories · arXiv:2506.16994
-
Reversing Flow for Image Restoration 20 Jun 2025 · 0 repositories · arXiv:2506.16961
-
Speeding up Local Optimization in Vehicle Routing with Tensor-based GPU Acceleration 20 Jun 2025 · 0 repositories · arXiv:2506.17357
-
DiffO: Single-step Diffusion for Image Compression at Ultra-Low Bitrates 19 Jun 2025 · 1 repository · arXiv:2506.16572Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified (of 14 harvested samples) · 14 pointer-only (licence)
-
FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation 19 Jun 2025 · 0 repositories · arXiv:2506.16201
-
LLMs in Coding and their Impact on the Commercial Software Engineering Landscape 19 Jun 2025 · 0 repositories · arXiv:2506.16653
-
PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning 18 Jun 2025 · 0 repositories · arXiv:2506.15923
-
A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks 17 Jun 2025 · 1 repository · arXiv:2506.14464
-
Call To Speak To Someone At Frontier™️ Airlines Through Various Contact Options: The Ultimate Step Guide 17 Jun 2025 · 0 repositories
-
Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data 17 Jun 2025 · 1 repository · arXiv:2506.14704
-
DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification 17 Jun 2025 · 0 repositories · arXiv:2506.14667
-
SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning 17 Jun 2025 · 0 repositories · arXiv:2506.14648
-
sHGCN: Simplified hyperbolic graph convolutional neural networks 17 Jun 2025 · 1 repository · arXiv:2506.14438
-
SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting 17 Jun 2025 · 0 repositories · arXiv:2506.14742
-
Zeroth-Order Optimization is Secretly Single-Step Policy Optimization 17 Jun 2025 · 0 repositories · arXiv:2506.14460
-
A Regret Perspective on Online Selective Generation 16 Jun 2025 · 0 repositories · arXiv:2506.14067
-
Condition Monitoring with Machine Learning: A Data-Driven Framework for Quantifying Wind Turbine Energy Loss 16 Jun 2025 · 0 repositories · arXiv:2506.13012
-
DETRPose: Real-time end-to-end transformer model for multi-person pose estimation 16 Jun 2025 · 1 repository · arXiv:2506.13027
-
Joint Spectrum Sensing and Resource Allocation for OFDMA-based Underwater Acoustic Communications 16 Jun 2025 · 0 repositories · arXiv:2506.13008
-
Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Study 16 Jun 2025 · 0 repositories · arXiv:2506.13836
-
ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models 16 Jun 2025 · 0 repositories · arXiv:2506.13472
-
Interference Mitigation in STAR-RIS-Aided Multi-User Networks with Statistical CSI 15 Jun 2025 · 0 repositories · arXiv:2506.12964
-
Deep Fusion of Ultra-Low-Resolution Thermal Camera and Gyroscope Data for Lighting-Robust and Compute-Efficient Rotational Odometry 14 Jun 2025 · 0 repositories · arXiv:2506.12536
-
GroupNL: Low-Resource and Robust CNN Design over Cloud and Device 14 Jun 2025 · 0 repositories · arXiv:2506.12335
-
Maximal Speed of Glucose Change Significantly Distinguishes Prediabetes from Diabetes 14 Jun 2025 · 0 repositories · arXiv:2506.12567
-
Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning 14 Jun 2025 · 0 repositories · arXiv:2506.12497
-
FieldFormer: Self-supervised Reconstruction of Physical Fields via Tensor Attention Prior 13 Jun 2025 · 0 repositories · arXiv:2506.11629
-
Generative Representational Learning of Foundation Models for Recommendation 13 Jun 2025 · 0 repositories · arXiv:2506.11999
-
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies 13 Jun 2025 · 0 repositories · arXiv:2506.11948
-
Symmetric Sliding-Mode Control of Grid-Forming Inverters With Controllable Region Under AC and DC Sides Varying 13 Jun 2025 · 0 repositories · arXiv:2506.11504
-
Wi-CBR: WiFi-based Cross-domain Behavior Recognition via Multimodal Collaborative Awareness 13 Jun 2025 · 0 repositories · arXiv:2506.11616
-
Skillful joint probabilistic weather forecasting from marginals 12 Jun 2025 · 0 repositories · arXiv:2506.10772
-
OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics 12 Jun 2025 · 0 repositories · arXiv:2506.10862
-
Coupled reaction and diffusion governing interface evolution in solid-state batteries 12 Jun 2025 · 0 repositories · arXiv:2506.10944
-
BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP 12 Jun 2025 · 1 repository · arXiv:2506.10896
-
Intelligent Automation for FDI Facilitation: Optimizing Tariff Exemption Processes with OCR And Large Language Models 12 Jun 2025 · 0 repositories · arXiv:2506.12093
-
It's Not the Target, It's the Background: Rethinking Infrared Small Target Detection via Deep Patch-Free Low-Rank Representations 12 Jun 2025 · 1 repository · arXiv:2506.10425
-
MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices 12 Jun 2025 · 0 repositories · arXiv:2506.10443
-
PointGS: Point Attention-Aware Sparse View Synthesis with Gaussian Splatting 12 Jun 2025 · 0 repositories · arXiv:2506.10335
-
The Diffusion Duality 12 Jun 2025 · 1 repository · arXiv:2506.10892Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Improving the performance of optical inverse design of multilayer thin films using CNN-LSTM tandem neural networks 11 Jun 2025 · 0 repositories · arXiv:2506.10044
-
Discrete Scale-invariant Metric Learning for Efficient Collaborative Filtering 11 Jun 2025 · 1 repository · arXiv:2506.09898
-
DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos 11 Jun 2025 · 0 repositories · arXiv:2506.10242
-
Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning 11 Jun 2025 · 0 repositories · arXiv:2506.09498
-
Probability-One Optimization of Generalized Rayleigh Quotient Sum For Multi-Source Generalized Total Least-Squares 11 Jun 2025 · 0 repositories · arXiv:2506.09573
-
An Adaptive Method Stabilizing Activations for Enhanced Generalization 10 Jun 2025 · 1 repository · arXiv:2506.08353
-
Complex-Valued Holographic Radiance Fields 10 Jun 2025 · 0 repositories · arXiv:2506.08350
-
FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed 10 Jun 2025 · 0 repositories · arXiv:2506.09034
-
Low-resource domain adaptation while minimizing energy and hardware resource consumption 10 Jun 2025 · 0 repositories · arXiv:2506.08433
-
SurfR: Surface Reconstruction with Multi-scale Attention 10 Jun 2025 · 0 repositories · arXiv:2506.08635
-
The Invariant Zonotopic Set-Membership Filter for State Estimation on Groups 10 Jun 2025 · 0 repositories · arXiv:2506.08530
-
A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling 9 Jun 2025 · 1 repository · arXiv:2506.07969
-
Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory Distillation 9 Jun 2025 · 0 repositories · arXiv:2506.07822
Tasks archive 2025-07-28
20 shown of 1,515 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| GPU | 533 |
| Object Detection | 437 |
| object-detection | 416 |
| Semantic Segmentation | 327 |
| Reinforcement Learning | 316 |
| Reinforcement Learning (RL) | 309 |
| reinforcement-learning | 303 |
| Object | 298 |
| Language Modelling | 261 |
| Decoder | 239 |
| Segmentation | 238 |
| Autonomous Driving | 225 |
| Computational Efficiency | 221 |
| Language Modeling | 219 |
| Quantization | 216 |
| CPU | 215 |
| Image Classification | 190 |
| Retrieval | 188 |
| General Classification | 184 |
| Denoising | 172 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
The archive places this method in no collection.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections