AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Efficient Depth-Guided Urban View Synthesis

sheng miao, Jiaxin Huang, Dongfeng Bai, Weichao Qiu, Liu Bingbing, Andreas Geiger, Yiyi Liao

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 8 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 3D geometric-prior feature (depth point cloud) to the model (ablation)EDUS · KITTI-360 drop 50% feed-forwardPSNR: 15.71 -> 21.93Improved
add image-based 2D feature retrieval alongside 3D feature (ablation)EDUS · KITTI-360 drop 50% feed-forwardPSNR: 18.28 -> 21.93Improved
use modulated SPADE CNN instead of 3D U-Net (ablation)EDUS · KITTI-360 drop 50% feed-forwardPSNR: 21.49 -> 21.93Improved
add foreground/background/sky decomposition (ablation)EDUS · KITTI-360 drop 50% feed-forwardPSNR: 20.65 -> 21.93Improved
add LiDAR supervision during training (ablation)EDUS · KITTI-360 drop 50% feed-forwardPSNR: 21.75 -> 21.93Improved
add LiDAR supervision during training (ablation)EDUS · KITTI-360 drop 50% feed-forwardLPIPS: 0.189 -> 0.178Improved
use EDUS geometric priors instead of feature-matching generalizable NeRFs at higher sparsitygeneralizable NeRF · KITTI-360 drop 80% feed-forwardPSNR: 18.69 -> 19.63 (MuRF vs Ours)Improved
initialize test-time optimization from EDUS generalizable model instead of 3DGS point cloud3D GS · KITTI-360 drop 90% test-time optimizationPSNR: 17.46 -> 19.16Improved
EDUS versus 3D GS at 50% drop rateEDUS · KITTI-360 drop 50% test-time optimizationLPIPS: 0.109 -> 0.136Hurt
fine-tune only global feature volume with generalizable initializationEDUS · KITTI-360 test-time optimizationtraining time: ~51min -> ~5min (MixNeRF vs Ours at 50%)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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