AI Paper Atlas

Research map / 3D vision / 3D generation

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

Ruofan Liang, Zan Gojcic, Merlin Nimier-David, David Acuna, Nandita Vijaykumar, Sanja Fidler, Zian Wang

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 24 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
use DiPIR instead of lighting estimation baselines for object insertionDiPIR · PolyHaven (11 scenes)RMSE: 0.056 (StyleLight) -> 0.048Improved
use DiPIR instead of the baselines on Waymo driving scenesDiPIR · Waymo (48 scenes)user study preference: 67.4% to 77.8% preferred across baselinesImproved
DiPIR versus NLFE on twilight scenesDiPIR · Waymo twilightuser study preference: 44.4%Hurt
add LoRA personalization of the diffusion model (vs SDS w/o LoRA) (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 90.7% preferredImproved
use LDS loss instead of original SDS loss (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 74.1% preferredImproved
add concept preservation class images to personalization (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 64.8% preferredImproved
add optimizable tone-mapping curve (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 68.5% preferredImproved
add two-environment-map fusion (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 66.7% preferredImproved
replace dataset-update photometric loss on SDEdit edits with LDS guidance (ablation)DiPIR · Waymo outdoor driving ablationuser preference for full method: 85.2% preferredImproved

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