AI Paper Atlas

Research map / Benchmarks / TikTok

TikTok leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on TikTok. Best FVD: 117.81 (Ours, ICLR 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.

TikTok · FVD

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

#FVD ↓MethodPaperTopic
1117.81OursTowards Multiple Character Image Animation Through Enhancing Implicit Decoupling
ICLR 2025 · Table: Quantitative comparison
Editing and style transfer
2131.3DreamActor-M1DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance
ICCV 2025 · Table 1
Video generation
3139.01Animate-XAnimate-X: Universal Character Image Animation with Enhanced Motion Representation
ICLR 2025 · Appendix, TikTok results
Video generation
4140.62StableAnimator
SVD
StableAnimator: High-Quality Identity-Preserving Human Image Animation
CVPR 2025 · Table 1
Editing and style transfer
5142.6DirectAnimatorBeyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
ICLR 2026 · Table 1
Video generation
6149.95SerialGen standardization modelSerialGen: Personalized Image Generation by First Standardization Then Personalization
CVPR 2025 · text
Text-to-image diffusion
7153.07DreamDance
Stable Video Diffusion
DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses
ICCV 2025 · Table 1a
Face and shape
8160.82Champ (fine-tuned on TikTok)Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
ECCV 2024 · Table 1
Human pose estimation
9179.07MagicAnimateMagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
CVPR 2024 · Table 1a
Video generation
10190.82RASA (Ours)
1.3B DiT
RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation
ECCV 2026 · Table 1
Video generation
3 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

TikTok · LPIPS

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

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