AI Paper Atlas

Research map / 3D vision / 3D generation

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Eric R. Chan, Koki Nagano, Matthew A. Chan, Alexander W. Bergman, Jeong Joon Park, Axel Levy, Miika Aittala, Shalini De Mello, Tero Karras, Gordon Wetzstein

ICCV 2023 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 211 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 3D feature volume geometry prior instead of geometry-free input concatenation (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)FID: 16.68 -> 6.47Improved
add geometry prior (feature volume) instead of geometry-free (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)LPIPS: 0.342 -> 0.104Improved
add MLP decoder to the feature volume instead of explicit representation (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)FID: 8.09 -> 6.47Improved
use iterative diffusion sampling instead of one-step inference (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)FID: 42.07 -> 6.47Improved
use iterative diffusion sampling instead of one-step inference (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)PSNR: 23.2 -> 20.7Hurt
use iterative diffusion sampling instead of one-step inference (ablation)3D-aware diffusion NVS · CO3D hydrantKID: 0.106 -> 0.012Improved
add autoregressive conditioning on previously generated frames (ablation)3D-aware diffusion NVS · ShapeNet cars (single view)FID: 6.47 -> 11.08Hurt
add autoregressive conditioning for sequence generation (ablation)3D-aware diffusion NVS · generated sequences (qualitative)geometric consistencyImproved
add classifier-free guidance during autoregressive generation (ablation)autoregressive sequence generation · ShapeNet (qualitative)sequence qualityHurt
use feature-volume aggregation instead of stochastic conditioning (ablation)autoregressive generation · COLMAP 3D consistency (qualitative)denoising steps per view: 256 -> 25 steps (10x speed)Improved
replace mean-pooling with max-pooling or weighted pooling for multi-view aggregation (ablation)multi-view feature aggregation · multi-view conditioningqualityNo clear effect
add more input views (ablation)3D-aware diffusion NVS · ShapeNet cars (qualitative)pixel-wise std of novel renderingsImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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