AI Paper Atlas

Research map / 3D vision / Depth and stereo

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

Ulrich Prestel, Stefan Andreas Baumann, Nick Stracke, Bjorn Ommer

ECCV 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 1 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 dynamic state prediction to the RayZer-like baseline (ablation)RayDer-S (SA-V) · RE10K NVSPSNR: 22.53 -> 24.01Improved
add dynamic state prediction (camera estimation side effect) (ablation)RayDer-S (SA-V) · DL3DV-10k camera estimationR@10: 59.8 -> 56.1Hurt
add state dropout on top of dynamic state (ablation)RayDer-S (SA-V) · DL3DV-10k camera estimationR@10: 56.1 -> 62.4Improved
add state dropout (inference without state) (ablation)RayDer-S (SA-V) · RE10K NVS without statePSNR: 13.42 -> 23.01Improved
add single-network consolidation of the three networks (ablation)RayDer-S (SA-V) · RE10K NVSPSNR: 23.76 -> 25.33Improved
add single-network consolidation (ablation)RayDer-S (SA-V) · DL3DV-10k camera estimationR@10: 62.4 -> 68.8Improved
add parallel-target attention (ablation)RayDer-S (SA-V) · RE10K NVSPSNR: 25.33 -> 25.12Mixed
add ordered autoregression over views (ablation)RayDer-S (SA-V) · RE10K NVS / DL3DV cameraPSNR / R@10: PSNR 25.12 -> 24.49; R@10 70.1 -> 73.6Mixed
use random-order autoregression instead of no autoregression (ablation)RayDer-S (SA-V) · RE10K NVSPSNR: 25.12 -> 26.28Improved
add random-order autoregression (ablation)RayDer-S (SA-V) · DL3DV-10k camera estimationR@10: 70.1 -> 84.4Improved
add local high-resolution layers (ablation)RayDer-S (SA-V) · RE10K NVSPSNR: 26.28 -> 26.87Improved
add random-order autoregression (SV-HQ training) (ablation)RayDer-S (SV-HQ) · RE10K NVSPSNR: 26.21 -> 29.57Improved

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