AI Paper Atlas

Research map / 3D vision / 3D generation

Text-To-4D Dynamic Scene Generation

ICML 2023 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 23 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use MAV3D rather than frame-wise Make-A-Video-to-3D baselinesText-to-4D generation · Text-to-4DR-Precision: 8.8, 10.6, 6.2 -> 83.7Helped
Use static scene pre-training before dynamic optimization (ablation)MAV3D · Text-to-4DR-Precision: 63.5 -> 83.7Helped
Add super-resolution fine-tuning (ablation)MAV3D · Text-to-4Dvideo qualityHelped
Use dynamic camera trajectories rather than a fixed camera (ablation)MAV3D · Text-to-4Damount of motionHelped
Add Gaussian annealing during dynamic optimization (ablation)MAV3D · Text-to-4Dmotion realismHelped
Replace HexPlane with D-NeRF (ablation)MAV3D · Text-to-4Doverall qualityHurt
Replace the static NeRF backbone with Instant-NGP (ablation)MAV3D · Text-to-4Dhuman preferenceHurt
Increase static pre-training beyond 2000 iterations (ablation)MAV3D · Text-to-4Dscene qualityNo 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