AI Paper Atlas

Research map / Benchmarks / Xiph-4K

Xiph-4K leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Xiph-4K. Best PSNR: 35.4 (HiFI, AAAI 2025).

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.

Xiph-4K · PSNR

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

#PSNR ↑MethodPaperTopic
135.4HiFIHigh-Resolution Frame Interpolation with Patch-based Cascaded Diffusion
AAAI 2025 · Table 1
Autoregressive and latent generation
234.83MASS (Ours)MASS: Motion-Aligned Selective Scan for Flow-Based Video Frame Interpolation
ECCV 2026 · Table 1
Video segmentation and tracking
334.72IQ-VFIIQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation
CVPR 2024 · Table 1
Video segmentation and tracking
434.67OursExtracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
CVPR 2023 · Table 1
Video segmentation and tracking
534.62VFIMambaVFIMamba: Video Frame Interpolation with State Space Models
NeurIPS 2024 · Table 2
Video segmentation and tracking
634.51FLAVR trained on LAVIB
FLAVR
LAVIB: A Large-scale Video Interpolation Benchmark
NeurIPS 2024 · Xiph4K performance table
Video segmentation and tracking
734.49Ours-PLC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation
CVPR 2025 · Table 1
Video segmentation and tracking
834.48BiFormerBiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
CVPR 2023 · Table 1
Video segmentation and tracking
934.29EMA-VFI + IAM-VFI
EMA-VFI
IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with motion complexity map
ECCV 2024 · Table 3
Video segmentation and tracking
1034.28RAFT-M2M++Video Frame Interpolation With Many-to-Many Splatting and Spatial Selective Refinement
TPAMI 2023 · Table 1
Video segmentation and tracking
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

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