SOTAVerified

Video Reconstruction

Source: Deep-SloMo

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 145 papers

TitleStatusHype
Image and Video Tokenization with Binary Spherical QuantizationCode3
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting—0
Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction—0
VideoQA-SC: Adaptive Semantic Communication for Video Question Answering—0
Bilateral Event Mining and Complementary for Event Stream Super-ResolutionCode1
Coherent 3D Portrait Video Reconstruction via Triplane Fusion—0
Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment NetworkCode1
EVAN: Evolutional Video Streaming Adaptation via Neural Representation—0
Collaborative Feedback Discriminative Propagation for Video Super-ResolutionCode1
Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution—0
EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition—0
Enhanced Event-Based Video Reconstruction with Motion Compensation—0
HDRFlow: Real-Time HDR Video Reconstruction with Large Motions—0
Place Anything into Any Video—0
Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation—0
Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering—0
EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset—0
Towards 4D Human Video StylizationCode0
Animatable Virtual Humans: Learning pose-dependent human representations in UV space for interactive performance synthesis—0
BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fields—0
Mapping EEG Signals to Visual Stimuli: A Deep Learning Approach to Match vs. Mismatch Classification—0
An Asynchronous Linear Filter Architecture for Hybrid Event-Frame CamerasCode1
LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video ReconstructionCode1
RIGID: Recurrent GAN Inversion and Editing of Real Face Videos—0
CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution—0
Semi Supervised Meta Learning for Spatiotemporal Learning—0
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision—0
Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint—0
Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from EventsCode0
Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity—0
HyperE2VID: Improving Event-Based Video Reconstruction via HypernetworksCode1
EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video ReconstructionCode1
LaMD: Latent Motion Diffusion for Image-Conditional Video Generation—0
Discovering Structure From Corruption for Unsupervised Image Reconstruction—0
HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains—0
RED-PSM: Regularization by Denoising of Factorized Low Rank Models for Dynamic ImagingCode0
HNeRV: A Hybrid Neural Representation for VideosCode1
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure TimeCode1
Deep Learning for Event-based Vision: A Comprehensive Survey and BenchmarksCode1
Parkinson gait modelling from an anomaly deep representation—0
1000 FPS HDR Video With a Spike-RGB Hybrid Camera—0
Learning Event Guided High Dynamic Range Video ReconstructionCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos—0
DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction—0
Spatial-Temporal Transformer for Video Snapshot Compressive ImagingCode1
PS-NeRV: Patch-wise Stylized Neural Representations for Videos—0
Synthesizing Light Field Video from Monocular VideoCode1
E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal ContextCode1
E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations—0
Show:102550
← PrevPage 2 of 3Next →
All datasetsUVGEvent-Camera DatasetMVSECMGifTai-Chi-HD (256)Tai-Chi-HD (512)TED-talksVoxCelebTai-Chi-HD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HiNeRVAverage PSNR (dB)38.02—Unverified
2CoordFlowAverage PSNR (dB)36.54—Unverified
3FFNeRVAverage PSNR (dB)35.63—Unverified
4HNeRVAverage PSNR (dB)35.23—Unverified
5E-NeRVAverage PSNR (dB)34.85—Unverified
6PS-NeRVAverage PSNR (dB)34.61—Unverified
7NeRVAverage PSNR (dB)34.49—Unverified
#ModelMetricClaimedVerifiedStatus
1E2VIDMean Squared Error0.18—Unverified
2E2VID+Mean Squared Error0.07—Unverified
3ET-NetMean Squared Error0.05—Unverified
4HyperE2VIDMean Squared Error0.03—Unverified
#ModelMetricClaimedVerifiedStatus
1E2VIDMean Squared Error0.23—Unverified
2E2VID+Mean Squared Error0.13—Unverified
3ET-NetMean Squared Error0.11—Unverified
4HyperE2VIDMean Squared Error0.08—Unverified
#ModelMetricClaimedVerifiedStatus
1FOMML10.02—Unverified
2Siarohin et al.L10.02—Unverified
#ModelMetricClaimedVerifiedStatus
1FOMMAED0.17—Unverified
2Siarohin et al.AED0.15—Unverified
#ModelMetricClaimedVerifiedStatus
1FOMMAED0.2—Unverified
2Siarohin et al.AED0.17—Unverified
#ModelMetricClaimedVerifiedStatus
1FOMMAED0.16—Unverified
2Siarohin et al.AED0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1FOMMAED0.13—Unverified
2Siarohin et al.AED0.13—Unverified
#ModelMetricClaimedVerifiedStatus
1First Order MotionL10.06—Unverified