AI Paper Atlas

Research map / 3D vision / 3D generation

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction

Xi Liu, Weiwei Sun, Zhou Ren, Chris Broaddus, Siyu Huang, Laurent Guigues

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 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
replace Difix3D diffusion prior with hallucination-aware prior (HAD) (ablation)3DGS pipeline · DL3DV (9 sparse views)PSNR: 21.355 -> 21.779Improved
add multi-sampling (3 versions) to HAD (ablation)HAD · DL3DV (9 sparse views)PSNR: 21.779 -> 21.983Improved
use single-phase 3DGS training with HAD, full model (ablation)HAD · DL3DV (9 sparse views)PSNR: 21.983 -> 22.134Improved
increase multi-sampling versions from 1 to 2 (ablation)HAD · DL3DV (9 sparse views)PSNR: 21.779 -> 21.938Improved
increase multi-sampling versions from 2 to 3 (ablation)HAD · DL3DV (9 sparse views)PSNR: 21.938 -> 21.983Improved
ArgMin fusion instead of weighted average (ablation)HAD multi-sampling · DL3DV (9 sparse views)PSNR: 21.856 -> 22.134Improved
use pretrained multiview encoder in score network (ablation)hallucination score network · Score estimation test scenesMAE: 0.054 -> 0.043Improved
use LVSM-based score network rather than retrained Difix3D estimator (ablation)hallucination score network · Score estimation test scenesMAE: 0.058 -> 0.043Improved
apply HAD in dense-view settingDifix3D (Gsplat-MCMC) · DL3DV (24 dense views)PSNR: 26.770 -> 26.969Improved
replace Difix3D with HADGsplat-mcmc · MipNeRF360 (9 input views)PSNR: 18.001 -> 18.689Improved
post-rendering refinement with diffusion priorDifix3D and HAD · DL3DV (9 sparse views)PSNR: 21.355 -> 20.673 PSNR; 0.199 -> 0.181 LPIPSMixed

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