AI Paper Atlas

Research map / Video / Video generation

PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories

Gemma Canet Tarrés, Manel Baradad, Francesc Moreno-Noguer, Yumeng Li

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 2 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
fine-tune Wan 2.1 on synthetic-trajectory compositing data (ablation)Wan 2.1 I2V-14B · Multi-object compositing benchmarkChamfer: 7.746 -> 5.754Improved
fine-tune Wan 2.1 on synthetic-trajectory compositing data (ablation)Wan 2.1 I2V-14B · Multi-object compositing benchmarkDINO: 0.446 -> 0.415Hurt
add full-resolution object and background image conditioning (ablation)PLACID · Multi-object compositing benchmarkChamfer: 5.754 -> 4.138Improved
add full-resolution object and background image conditioning (ablation)PLACID · Multi-object compositing benchmarkDINO: 0.415 -> 0.440Improved
add object-aware text tokens (ablation)PLACID · Multi-object compositing benchmarkMSE-BG: 0.040 -> 0.033Improved
add object-aware text tokens (ablation)PLACID · Multi-object compositing benchmarkMissing: 0.042 -> 0.051Hurt
compute loss only on the last frame for Subject-200k data (ablation)PLACID · Multi-object compositing benchmarkMSE-BG: 0.033 -> 0.019Improved
compute loss only on the last frame for Subject-200k data (ablation)PLACID · Multi-object compositing benchmarkMissing: 0.051 -> 0.044Improved
combine all four data sources instead of Subject-200k only (ablation)PLACID · Multi-object compositing benchmarkMSE-BG: 0.129 -> 0.019Improved
combine all data sources instead of In-the-Wild only (ablation)PLACID · Multi-object compositing benchmarkDINO: 0.465 -> 0.440Hurt
use PLACID instead of base Wan 2.1Wan 2.1 I2V-14B · Multi-object compositing benchmarkChamfer: 7.746 -> 4.641Improved
use PLACID instead of base Wan 2.1Wan 2.1 I2V-14B · Multi-object compositing benchmarkCLIP-I: 0.711 -> 0.705No clear effect

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