AI Paper Atlas

Research map / Benchmarks / SPMCS

SPMCS leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SPMCS. Best PSNR: 25.32 (Upscale-A-Video, CVPR 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.

SPMCS · PSNR

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

#PSNR ↑MethodPaperTopic
125.32Upscale-A-Video
SD ×4 Upscaler
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
CVPR 2024 · Table 1
Video generation
223.82WEVSR
WAN-2.1
WEVSR: Video Diffusion Generators for Real-World Video Super‑Resolution with Wavelet-Enhanced VAE Encoder
ICML 2026 · Table 1
Super-resolution
323.18TRaM-VSR (Ours)TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution
ECCV 2026 · Table 1
Video segmentation and tracking
423.11DOVE
CogVideoX1.5
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
NeurIPS 2025 · Quantitative comparison table
Super-resolution
523.04SparkVSR (no ref)
CogVideoX1.5-5B I2V
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
ECCV 2026 · Table 1
Video segmentation and tracking
622.9DUO-VSRDUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution
CVPR 2026 · Table 1
Super-resolution
722.76DTG-Restore (Ours)DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
CVPR 2026 · Table 1
Video generation
822.17SCST
Stable Diffusion V2.1
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution
CVPR 2025 · Table 1
Video segmentation and tracking
922.092PS-SRPS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
CVPR 2026 · Table 1
Super-resolution
1021.73Vivid-VR
CogVideoX1.5-5B
Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
ICLR 2026 · Table 1
Video generation
1 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

SPMCS · LPIPS

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

#LPIPS ↓MethodPaperTopic
10.222Upscale-A-Video
SD ×4 Upscaler
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
CVPR 2024 · Table 1
Video generation
20.26SCST
Stable Diffusion V2.1
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution
CVPR 2025 · Table 1
Video segmentation and tracking
30.278Vivid-VR
CogVideoX1.5-5B
Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
ICLR 2026 · Table 1
Video generation
40.2865SkipSR-3B
SeedVR-3B
SkipSR: Faster Super-Resolution with Token Skipping
NeurIPS 2026 · Table 2
Video segmentation and tracking
50.2883TRaM-VSR (Ours)TRaM-VSR: Importance-Aware Token Routing and Merging for One-Step Diffusion Video Super-Resolution
ECCV 2026 · Table 1
Video segmentation and tracking
60.294PS-SRPS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
CVPR 2026 · Table 1
Super-resolution
70.294WEVSR
WAN-2.1
WEVSR: Video Diffusion Generators for Real-World Video Super‑Resolution with Wavelet-Enhanced VAE Encoder
ICML 2026 · Table 1
Super-resolution
80.3166InfVSR
Wan 2.1 1.3B
InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
ICML 2026 · Table 1
Video generation
90.375DLoRAL
Stable Diffusion 2.1
One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
NeurIPS 2025 · Table 1
Video generation
100.408DTG-Restore (Ours)DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
CVPR 2026 · Table 1
Video generation

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