AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation

Guosheng Zhao, Xiaofeng Wang, Chaojun Ni, Zheng Zhu, Wenkang Qin, Guan Huang, Xingang Wang

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 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 depth loss with fused static point clouds on novel views (ablation)ReconDreamer · Waymo, lane shift 3mFID: 93.56 -> 77.51Improved
add depth loss with fused static point clouds on novel views (ablation)ReconDreamer · Waymo, lane shift 0mLPIPS: 0.1519 -> 0.1207Improved
add separate ground Gaussian model (ablation)ReconDreamer + depth loss · Waymo, lane shift 3mFID: 77.51 -> 75.22Improved
add separate ground Gaussian model (ablation)ReconDreamer + depth loss · Waymo, lane shift 6mNTL-IoU: 53.55 -> 55.34Improved
add separate ground Gaussian model (ablation)ReconDreamer + depth loss · Waymo, lane shift 0mPSNR: 35.13 -> 34.93Hurt
add NTDNet (ablation)ReconDreamer + depth loss + ground model · Waymo, lane shift 0mPSNR: 34.93 -> 36.29Improved
add NTDNet (ablation)ReconDreamer + depth loss + ground model · Waymo, lane shift 6mFID: 121.46 -> 111.92Improved
add NTDNet (ablation)ReconDreamer + depth loss + ground model · Waymo, lane shift 0mLPIPS: 0.1174 -> 0.1076Improved
full ReconDreamer++ versus ReconDreamerReconDreamer · Waymo, lane shift 0mLPIPS: 0.1519 -> 0.1076Improved
full ReconDreamer++ versus ReconDreamerReconDreamer · Waymo, lane shift 3mFID: 93.56 -> 72.02Improved
full ReconDreamer++ versus ReconDreamerReconDreamer · nuScenes, lane shift 3mNTA-IoU: 0.325 -> 0.365Improved
full ReconDreamer++ versus ReconDreamerReconDreamer · EUVS test set (Level 1)LPIPS: 0.3286 -> 0.3057Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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