AI Paper Atlas

Research map / 3D vision / Gaussian splatting

High-Resolution and Few-shot View Synthesis from Asymmetric Dual-lens Inputs

Ruikang Xu, Mingde Yao, Yue Li, Yueyi Zhang, Zhiwei Xiong

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 3 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 pre-upsampling of wide-angle images to the 3D-GS baseline (ablation)3D-GS + HAT · Simulated dataset 10-shotPSNR: 17.89 -> 18.65Improved
add depth-wise loss Rd (ablation)DL-GS pre-upsampling baseline · Simulated dataset 10-shotPSNR: 18.65 -> 19.03Improved
add dual-lens-consistent loss Rc (ablation)DL-GS · Simulated dataset 10-shotPSNR: 19.03 -> 19.40Improved
add wide-angle reference branch in refinement module (ablation)DL-GS · Simulated dataset 90-shotPSNR: 25.08 -> 25.35Improved
add telephoto reference branch in refinement module (ablation)DL-GS · Simulated dataset 90-shotPSNR: 25.35 -> 25.61Improved
use dual-lens regularization instead of monocular-depth few-shot methods (FSGS + HAT)3D-GS · Real-captured forward-facing 5-shotPSNR: 23.08 -> 24.05Improved
DL-GS versus NeRF-SR in dense trainingDL-GS · Simulated dataset 20-shot SSIM vs DS-NeRFPSNR: 21.54 -> 21.77Improved
replace NeRF-based methods with 3D-GS-based DL-GSDL-GS · Simulated 10-shot training timetraining time: 5h 8min -> 14min 35sImproved
NeRF-SR without few-shot regularizationNeRF-SR · Real-captured forward-facing 5-shotPSNR: 12.53 (5-shot) vs 30.53 (50-shot)Hurt

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