AI Paper Atlas

Research map / Video / Video generation

InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

Hoiyeong Jin, Hyojin Jang, Junha Hyung, Jeongho Kim, Kinam Kim, Dongjin Kim, Huijin choi, Hyeonji Kim, Choo Jaegul

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 9 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
add Optics-Aware Representation Alignment loss (ablation)ROSE++ LoRA VACE · ROSE++ held-out (25 samples), Optics maskPSNR: 19.9065 -> 27.2362Improved
add alignment loss (ablation)ROSE++ LoRA VACE · ROSE++ held-out (25 samples), Object maskPSNR: 26.0282 -> 25.8785No clear effect
add alignment loss (ablation)ROSE++ LoRA VACE · ROSE++ held-out (25 samples), unedited regionPSNR: 33.31 -> 33.30No clear effect
fine-tune VACE on ROSE++ with 4D mask (ablation)VACE (our mask) · VOIBenchCLIP-I: 0.7368 -> 0.7485Improved
use coarse bbox mask instead of 4D mask when fine-tuning on ROSE++ (ablation)VACE ROSE++ · VOIBenchCLIP-I: 0.7485 -> 0.6383Hurt
add first-frame anchoring (ablation)4D mask VACE · VOIBenchDINO-I: 0.3861 -> 0.5135Improved
add first-frame anchoring (ablation)4D mask VACE · VOIBenchBackground Consistency: 0.9232 -> 0.9175Hurt
add ROSE++ LoRA fine-tuning (ablation)anchored VACE · VOIBenchImaging Quality: 0.6318 -> 0.7101Improved
add alignment loss on top of LoRA (ablation)Config (c) · VOIBenchImaging Quality: 0.7101 -> 0.7473Improved
add alignment loss on top of LoRA (ablation)Config (c) · VOIBenchDINO-I: 0.5678 -> 0.5669No clear effect
use ROSE++ generated references instead of random-frame crops (ablation)Ours · VOIBenchMulti-View Consistency: 0.5295 -> 0.5865Improved
4D-aware mask plus optics-aware pipeline vs KlingInsertAnywhere · VOIBenchCLIP-I: 0.6349 -> 0.8132Improved

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