AI Paper Atlas

Research map / 3D vision / 3D generation

VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents

George Eskandar, Fengyi Shen, Mohammad Altillawi, Dong Chen, Yang Bai, Liudi Yang, Ziyuan Liu

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 0 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
inject 4D point cloud (Pi3) into latent space (ablation)VideoWeaver multi-view · Droid testMet3R: 0.481 -> 0.533Improved
inject 4D point cloud (Pi3) into latent space (ablation)VideoWeaver multi-view · Agibot testMet3R: 0.597 -> 0.612Improved
add heterogeneous-timestep training (conditional on one view) (ablation)VideoWeaver multi-view · Droid testMet3R: 0.533 -> 0.578Improved
add heterogeneous-timestep training (conditional on one view) (ablation)VideoWeaver multi-view · Agibot testMet3R: 0.612 -> 0.624Improved
fuse depth and sketch with MoE instead of sketch only (ablation)VideoWeaver single-view · Bridge testDepth siRMSE: 0.245 -> 0.158Improved
fuse depth and sketch with MoE instead of sketch only (ablation)VideoWeaver single-view · Bridge testVBench: 0.833 -> 0.837No clear effect
fuse depth and sketch with MoE instead of depth only (ablation)VideoWeaver single-view · Bridge testEdge-F1: 0.250 -> 0.393Improved
drop sketch at inference with MoE model (ablation)VideoWeaver single-view · Bridge testEdge-F1: 0.393 -> 0.171Hurt
use multi-view model instead of single-view (ablation)VideoWeaver · Droid testDepth siRMSE: 0.362 -> 0.347Improved
use multi-view model instead of single-view (ablation)VideoWeaver · Droid testJEDi: 0.384 -> 0.509Hurt
use VideoWeaver single-view instead of VACEVACE · Droid testVBench: 0.729 -> 0.732No 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