AI Paper Atlas

Research map / Video / Video generation

Anchor Frame Bridging for Coherent First-Last Frame Video Generation

Xuehan Hou, Meng Fan, Pengchong Qiao, Zesen Cheng, Yian Zhao, Lei Zhu, Kaiwen Cheng, Chang Liu, Jie Chen

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AFB anchor frame to Wan2.1 first-last frame generationWan2.1-FLF2V · Own FLF2V dataset (436 pairs, 5s)FVD: 413.68 -> 375.12Improved
add AFB anchor frame to Wan2.1-I2VWan2.1-I2V · Own FLF2V dataset (436 pairs, 5s)PSNR: 32.13 -> 35.41Improved
add AFB to HunyuanVideo-I2VHunyuanVideo-I2V · Own FLF2V dataset (436 pairs, 5s)FVD: 496.32 -> 435.71Improved
use a single anchor frame rather than two (ablation)Wan2.1 + AFB · Own FLF2V dataset (436 pairs, 5s)FVD: 386.94 -> 375.12Improved
use a single anchor frame rather than three (ablation)Wan2.1 + AFB · Own FLF2V dataset (436 pairs, 5s)PSNR: 30.49 -> 35.41Improved
increase reverse-denoising stop step K from 5 to 50 (ablation)Wan2.1 + AFB · Own FLF2V dataset (436 pairs, 5s)FVD: 412.73 -> 375.12Improved
stop at K=15 instead of full reverse pass (ablation)Wan2.1 + AFB · Own FLF2V dataset (436 pairs, 5s)FVD: 388.45 vs 375.12 (+35% time)Mixed
use Qwen-generated prompts instead of a general prompt (ablation)Wan2.1 + AFB · Own FLF2V dataset (436 pairs, 5s)FVD: 475.33 -> 375.12Improved
add AFB under a general text prompt (ablation)Wan2.1 · Own FLF2V dataset (436 pairs, 5s)FVD: 486.23 -> 475.33Improved
add AFB versus FCVG on 5s videosFCVG · Own FLF2V dataset (436 pairs, 5s)FVD: 438.83 -> 375.12Improved
add AFB versus MoG on 5s videosMoG · Own FLF2V dataset (436 pairs, 5s)PSNR: 18.41 -> 35.41Improved
average anchor latent with noise latent at each step instead of direct conditioning (ablation)Wan2.1 + AFB · qualitative examplesvisual qualityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy