AI Paper Atlas

Research map / 3D vision / 3D generation

The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D Knowledge

Haoru Wang, Kai Ye, Minghan Qin, Yangyan Li, Wenzheng Chen, Baoquan Chen

ICLR 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations

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
reduce explicit 3D scene structure (LVSM vs MVSplat)feed-forward NVS · RealEstate10K scalabilityavg PSNR gain per 4x data: 0.39 -> 0.64Improved
remove input pose requirement (PT-LVSM vs LVSM)feed-forward NVS · RealEstate10K scalabilityavg PSNR gain per 4x data: 0.64 -> 1.72Improved
remove target pose requirement (UP-LVSM vs PT-LVSM)feed-forward NVS · RealEstate10K scalabilityavg PSNR gain per 4x data: 1.72 -> 2.63Improved
explicit 3D structure at low data (NoPoSplat/MVSplat vs implicit)feed-forward NVS · RealEstate10K little subset (1K scenes)PSNR: MVSplat 25.24 vs PT-LVSM 20.80Mixed
use latent Plucker learner rather than SfM target poses (ablation)UP-LVSM · RealEstate10KPSNR: 26.00 -> 28.82Improved
use latent Plucker learner rather than key-value pose estimator (ablation)UP-LVSM · RealEstate10KPSNR: 20.92 -> 28.82Improved
train UP-LVSM without any poses vs pose-dependent LVSMUP-LVSM · RealEstate10K full evalPSNR: 27.60 -> 28.82Improved
less dependence at small data on ACID: UP-LVSM at 0.8K scenesUP-LVSM · ACID 0.8K scenesPSNR: LVSM 23.43 vs UP-LVSM 15.92Hurt
train on RealEstate10K and test zero-shot on ACIDUP-LVSM · ACIDPSNR: 27.21 -> 27.33Improved
pose-free UP-LVSM on Objaverse at 128K objects vs LVSMUP-LVSM · Objaverse 128K objectsPSNR: 30.22 vs 26.12Hurt
fine-tune with linear SE(3)-to-latent mapper on 1202 posed scenesUP-LVSM · RealEstate10KPSNRNo clear effect

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