AI Paper Atlas

Research map / Video / Video generation

Tempo-SAM3D: Monocular Video to 4D via Temporal Memory-Guided Generation

Baicheng Li, Dong Wu, Yingdian Cao, Haoxiang Yang, Yiwen Lu, Zike Yan, Hongbin Zha

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation · 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
add self-attention memory (ablation)SAM3D · Tempo-SAM3D datasetFVD: 1218.63 -> 1076.52Improved
add self-attention memory (ablation)SAM3D · Tempo-SAM3D datasetLPIPS: 0.128 -> 0.131No clear effect
add self-attention memory (ablation)SAM3D · Tempo-SAM3D datasetACC5cm: 90.3 -> 89.8No clear effect
add temporal guidance (ablation)SAM3D + self-attn memory · Tempo-SAM3D datasetFVD: 1076.52 -> 935.18Improved
add alignment guidance (ablation)SAM3D + memory + temporal guidance · Tempo-SAM3D datasetFVD: 935.18 -> 871.25Improved
add alignment guidance (ablation)SAM3D + memory + temporal guidance · Tempo-SAM3D datasetIoU: 73.3 -> 82.6Improved
add alignment guidance (ablation)SAM3D + memory + temporal guidance · Tempo-SAM3D datasetACC5cm: 90.1 -> 95.2Improved
add HexPlane temporal smoothing (ablation)Tempo-SAM3D w/o HexPlane · Tempo-SAM3D datasetFVD: 871.25 -> 732.45Improved
add HexPlane temporal smoothing (ablation)Tempo-SAM3D w/o HexPlane · Tempo-SAM3D datasetPSNR: 20.18 -> 20.12No clear effect
add cross-attention visual memory (ablation)Tempo-SAM3D · construction worker sequenceappearance consistencyImproved
use Tempo-SAM3D instead of V2M4V2M4 benchmark · Simple (Consistent4D)FVD: 825.59 -> 841.27Hurt
use Tempo-SAM3D instead of V2M4V2M4 benchmark · Complex (Mixamo & Sketchfab)FVD: 666.04 -> 642.38Improved

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