AI Paper Atlas

Research map / 3D vision / 3D generation

Grounded Latents for Entity-Centric 4D Scene Generation

Jinhyung Park, Navyata Sanghvi, Erica Weng, Shawn Hunt, Shinya Tanaka, Hironobu Fujiyoshi, Kris Kitani

CVPR 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation

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
increase number of latents from 256 to 768 (ablation)LatentWorld · CarlaSCgeometry MMD: 13.32 -> 6.44Improved
increase number of latents from 768 to 1024 (ablation)LatentWorld · CarlaSCsemantics MMD: 11.30 -> 12.36Hurt
increase number of latents from 768 to 1024 (ablation)LatentWorld · CarlaSCreconstruction mIoU: 93.63 -> 94.71Improved
increase number of latents from 768 to 1024 (ablation)LatentWorld · CarlaSCgeometry+semantics MMD: 6.69 -> 7.30Hurt
add outpainting mean-shift guidance (lambda 1.0) (ablation)LatentWorld outpainting · Waymogeometry+semantics MMD: 2.31 -> 1.04Improved
increase outpainting push weight from 1.0 to 1.5 (ablation)LatentWorld outpainting · Waymogeometry+semantics MMD: 1.04 -> 1.09Hurt
replace dense voxel/grid generation with grounded 3D latentsDynamicCity · Waymo 4Dgeometry+semantics MMD: 2.61 -> 0.96Improved
replace grid-based generators with grounded latents on CarlaSCSemCity · CarlaSCgeometry MMD: 10.47 -> 6.44Improved
grounded latents vs grid baselines on semantics-only metricPDD/SemCity/DynamicCity · CarlaSCsemantics MMD: 12.74 -> 11.30Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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