AI Paper Atlas

Research map / 3D vision / Depth and stereo

Syn4D: A Multiview Synthetic 4D Dataset

Zeren Jiang, Yushi Lan, Yihang Luo, Yufan Deng, Zihang Lai, Edgar Sucar, Christian Rupprecht, Iro Laina, Diane Larlus, Chuanxia Zheng, Andrea Vedaldi

ECCV 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 5 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 the geometry-aware NVS model on Syn4D instead of Kubric (ablation)ReCamMaster-based multiview diffusion · Syn4D NVS benchmarkFVD: 631 -> 452Improved
train the geometry-aware NVS model on Syn4D instead of Kubric (ablation)ReCamMaster-based multiview diffusion · Syn4D NVS benchmarkFVD-P: 229 -> 139Improved
train the geometry-aware NVS model on Syn4D instead of Kubric (ablation)ReCamMaster-based multiview diffusion · Syn4D NVS benchmarkATE: 0.064 -> 0.070No clear effect
train the geometry-aware NVS model on Syn4D instead of Kubric (ablation)ReCamMaster-based multiview diffusion · ReCamMaster benchmark (zero-shot)FVD-V-P: 1307 -> 397.4Improved
match clip count (2048) and frames (49) between Kubric and Syn4D training (ablation)Ours (Syn4D) vs Ours (Kubric) · ReCamMaster benchmark (matched budget)FVD-V: 1964 -> 1566Improved
condition on ground-truth point map instead of DA3-estimated point map; Syn4D vs Kubric training (ablation)geometry-aware NVS model · Syn4D NVS benchmarkCOR: 0.236 -> 0.124Improved
co-train 4RC with Syn4D4RC · Syn4D Soviet dense trackingAPD: 58.35 -> 74.46Improved
co-train 4RC with Syn4D4RC · Syn4D Warehouse dense trackingEPE: 0.3302 -> 0.1915Improved
co-train 4RC with Syn4D4RC · ADT sparse 3D trackingAPD: 87.82 -> 89.44Improved
co-train 4RC with Syn4D4RC · Sintel camera poseATE: 0.144 -> 0.076Improved
co-train 4RC with Syn4D4RC · TUM-dynamics camera poseATE: 0.010 -> 0.012Hurt
co-train 4RC with Syn4D4RC · Sintel video depth (scale alignment)delta<1.25: 62.2 -> 74.6Improved

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