AI Paper Atlas

Research map / 3D vision / 3D generation

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

Jiazhe Guo, Yikang Ding, Xiwu Chen, Shuo Chen, Bohan Li, Yingshuang Zou, Xiaoyang Lyu, Feiyang Tan, Xiaojuan Qi, Zhiheng Li, Hao Zhao

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 37 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-supervised cycle consistency (SCC) fine-tuning (ablation)DiST-S · nuScenes NVS, shift 1mFID: 12.00 -> 10.12Improved
add SCC fine-tuning (ablation)DiST-S · nuScenes NVS, shift 4mFVD: 137.03 -> 105.29Improved
add SCC fine-tuning (ablation)DiST-4D · nuScenes NVS, shift 4mFID: 33.56 -> 25.16Improved
condition on generated DiST-T videos instead of real videos with metric depthDiST-S · nuScenes NVS, shift 1mFID: 12.00 -> 20.64Hurt
add valid mask to depth conditioning (ablation)DiST-S · DiST-S ablation FID-1mFID: 30.31 -> 25.51Improved
add depth modality without valid mask (ablation)DiST-S · DiST-S ablation FID-1mFID: 26.33 -> 30.31Hurt
add data augmentation (n=+-4 projection and downsampling) (ablation)DiST-S · DiST-S ablation FID-1mFID: 26.19 -> 25.51Improved
add reference depth as input to DiST-T (ablation)DiST-T · nuScenes val video generationFID: 6.83 -> 7.40Hurt
add reference depth as input to DiST-T (ablation)DiST-T · nuScenes depth generation, multi-frame GTAbs. Rel.: 0.24 -> 0.20Improved
use DiST-T instead of UniScene for video generationUniScene · nuScenes val video generationFVD: 71.94 -> 22.67Improved
use DiST-S (+SCC) instead of StreetGaussianStreetGaussian · nuScenes NVS, shift 1mFID: 32.12 -> 10.12Improved

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