AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

Giuseppe Stracquadanio, Kevin Raj, Julia Grabinski, Stefan Roth

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 0 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 3DGS-rasterized latent conditioning to the diffusion model (ablation)ReconSplat · RE10K extrapolation (before fine-tuning)image metricsImproved
model joint appearance-depth distribution instead of appearance only (ablation)ReconSplat · RE10K extrapolation (before fine-tuning)image-wise metricsMixed
add annealed multi-resolution noise (ablation)ReconSplat · RE10K extrapolation (before fine-tuning)FIDImproved
add 2x upsampled-input fine-tuning (f=8 to f=4) (ablation)ReconSplat · RE10Kimage-quality metricsImproved
train only 3D convolution blocks versus full fine-tuning (ablation)ReconSplat · RE10K video (MEt3R)multi-view consistency: 77M vs ~0.9B trainable parametersNo clear effect
use classifier-free guidance scale 3 instead of ~1 or >=5 (ablation)ReconSplat · RE10K and DL3DV-10Kperceptual metricsImproved
increase context views from 6 to 8 (ablation)ReconSplat · DL3DV-10KFID: 30.13 -> 27.40Improved
compare against LVSM on extrapolationReconSplat vs LVSM · RE10K extrapolationLPIPS: 0.172 vs 0.222Hurt
compare against LVSM on extrapolationReconSplat vs LVSM · RE10K extrapolationFID: 5.20 -> 4.89Improved
add generative refinement on regression 3DGS (vs DepthSplat) for extrapolationReconSplat vs DepthSplat · RE10K extrapolationFID: 11.81 -> 4.89Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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