AI Paper Atlas

Research map / Benchmarks / HQF

HQF leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on HQF. Best SSIM: 0.693 (DeblurSR, AAAI 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

HQF · SSIM

12 papers, each with its best reported number for its own method; higher is better.

#SSIM ↑MethodPaperTopic
10.693DeblurSRDeblurSR: Event-Based Motion Deblurring under the Spiking Representation
AAAI 2024 · Table 1
Video segmentation and tracking
20.676E2VID, WebVid10K
E2VID
V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation
NeurIPS 2025 · Table: Quantitative evaluation
Video segmentation and tracking
30.671E2HQVE2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
AAAI 2024 · Table 1
Video segmentation and tracking
40.643ET-NetEvent-Based Video Reconstruction Using Transformer
ICCV 2021 · Table 1
Video segmentation and tracking
50.585AE2VIDAE2VID: Event-based Video Reconstruction via Aperture Modulation
CVPR 2026 · Table 2
Video segmentation and tracking
60.575EventMambaEventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
AAAI 2025 · Table 1
Video segmentation and tracking
70.548LaSe-E2VLaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
NeurIPS 2024 · Quantitative comparison table
Video segmentation and tracking
80.532PA-EVSNNEvent-Based Video Reconstruction via Potential-Assisted Spiking Neural Network
CVPR 2022 · Comparison on IJRR, HQF, and M
Spiking networks
90.531EvINR (Ours)Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations
ECCV 2024 · Table 1
Video segmentation and tracking
100.48E2VID_E
E2VID
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
CVPR 2021 · Table: Quantitative evaluation
Depth and stereo
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

HQF · MSE

10 papers, each with its best reported number for its own method; lower is better.

#MSE ↓MethodPaperTopic
10.019E2HQVE2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
AAAI 2024 · Table 1
Video segmentation and tracking
20.031EventMambaEventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
AAAI 2025 · Table 1
Video segmentation and tracking
30.034LaSe-E2VLaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
NeurIPS 2024 · Quantitative comparison table
Video segmentation and tracking
40.0349ET-NetEvent-Based Video Reconstruction Using Transformer
ICCV 2021 · Table 1
Video segmentation and tracking
50.039AE2VIDAE2VID: Event-based Video Reconstruction via Aperture Modulation
CVPR 2026 · Table 2
Video segmentation and tracking
60.0441Ours
ETNet initial predictor
Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
ECCV 2024 · Table 1
Video generation
70.048EvINR (Ours)Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations
ECCV 2024 · Table 1
Video segmentation and tracking
80.06E2VID_E
E2VID
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
CVPR 2021 · Table: Quantitative evaluation
Depth and stereo
90.061PA-EVSNNEvent-Based Video Reconstruction via Potential-Assisted Spiking Neural Network
CVPR 2022 · Comparison on IJRR, HQF, and M
Spiking networks
100.089STLRSpike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction
ECCV 2024 · Table 1
Video segmentation and tracking

HQF · LPIPS

10 papers, each with its best reported number for its own method; lower is better.

#LPIPS ↓MethodPaperTopic
10.2039Ours
ETNet initial predictor
Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
ECCV 2024 · Table 1
Video generation
20.254LaSe-E2VLaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
NeurIPS 2024 · Quantitative comparison table
Video segmentation and tracking
30.261EventMambaEventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
AAAI 2025 · Table 1
Video segmentation and tracking
40.261E2HQVE2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
AAAI 2024 · Table 1
Video segmentation and tracking
50.274ET-NetEvent-Based Video Reconstruction Using Transformer
ICCV 2021 · Table 1
Video segmentation and tracking
60.333EvINR (Ours)Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations
ECCV 2024 · Table 1
Video segmentation and tracking
70.352AE2VIDAE2VID: Event-based Video Reconstruction via Aperture Modulation
CVPR 2026 · Table 2
Video segmentation and tracking
80.408STLRSpike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction
ECCV 2024 · Table 1
Video segmentation and tracking
90.416PA-EVSNNEvent-Based Video Reconstruction via Potential-Assisted Spiking Neural Network
CVPR 2022 · Comparison on IJRR, HQF, and M
Spiking networks
100.47E2VID_E
E2VID
Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
CVPR 2021 · Table: Quantitative evaluation
Depth and stereo

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.