AI Paper Atlas

Research map / Video / Video generation

Pix2Gif: Motion-Guided Diffusion for GIF Generation

Hitesh Kandala, Jianfeng Gao, Jianwei Yang

ECCV 2024 · Video › Video generation · approach: Efficient video diffusion models · 11 citations (OpenAlex)

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
train InstructPix2Pix on the curated TGIF data with a flow phrase appended (Pix2Gif-Base) (ablation)InstructPix2Pix · Motion coherency, cfg_img=1.4L2: 23.429 -> 7.580Improved
add motion embedding layer, warping module and perceptual loss to Pix2Gif-Base (ablation)Pix2Gif-Base · Motion coherency, cfg_img=1.4L2: 7.580 -> 1.746Improved
add motion embedding layer to encode motion magnitude (ablation)Pix2Gif-Base · image-video similarity (100 samples)source/target frame similarity scoreImproved
add warping module whose output replaces source feature as LDM input (Pix2Gif-Warp) (ablation)Pix2Gif · image-video similarity (100 samples)average similarity scoreHurt
concatenate warped feature with source image feature instead of adding (ablation)Pix2Gif · image-video similarity, cfg_img in [1.6, 2.2]average similarity scoreImproved
add perceptual loss on warped latent (ablation)Pix2Gif-Warp-concat · image-video similarity, cfg_img in [1.6, 2.2]motion consistency vs extent of motionMixed
Pix2Gif versus I2VGen-XL and DynamiCrafter on CLIPSimimage-text-to-video generation · UCF-101 and MSR-VTTCLIPSim: UCF-101: 0.2865 -> 0.2815Hurt
frame-by-frame image translation instead of full-sequence 3D video diffusionimage-to-GIF generation · UCF-101 zero-shotFVD: 527.06 -> 285.02Improved

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