AI Paper Atlas

Research map / 3D vision / 3D generation

GenRC: Generative 3D Room Completion from Sparse Image Collections

Ming-Feng Li, Yueh-Feng Ku, Hong-Xuan Yen, Chi Liu, Yu-Lun Liu, Albert Y Chen, Cheng-Hao Kuo, Min Sun

ECCV 2024 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 5 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 panorama inpainting instead of iterative novel-view filling (ablation)GenRC · ScanNet (5% input)depth MSE: 0.44 -> 0.27Improved
use E-Diffusion instead of plain MultiDiffusion for panorama inpainting (ablation)GenRC · ScanNet (5% input)PSNR: 13.8 -> 14.4Improved
add texture refinement (last 20 of 50 steps with MultiDiffusion) (ablation)GenRC · ScanNet (10% input)depth MSE: 0.21 -> 0.13Improved
add texture refinement (ablation)GenRC · ScanNet (5% input)PSNR: 14.6 -> 14.4No clear effect
add active sampling (3 panorama candidates, pick lowest depth MSE) (ablation)GenRC · ScanNet (5% input)depth MSE: 0.46 -> 0.27Improved
add textual inversion for the prompt token (ablation)GenRC · ScanNet (5% input)CLIP score: 0.792 -> 0.794Improved
add textual inversion for the prompt token (ablation)GenRC · ScanNet (5% input)PSNR: 14.7 -> 14.4Hurt
use 8 views in E-Diffusion instead of 6 or 16 (ablation)GenRC · ScanNet (5% input)depth MSE: 0.29 (6 views), 0.32 (16 views) -> 0.27Improved
use 20 texture refinement steps instead of 10 or 30 (ablation)GenRC · ScanNet (5% input)depth MSE: 0.37 (F=10), 0.35 (F=30) -> 0.27Improved
replace the Stable Diffusion-based GenRC by RGBD2 trained on ScanNet when moving to ARKitScenesRGBD2 · ARKitScenes (5% input)PSNR: 12.2 vs GenRC 13.2Hurt
use GenRC with shuffled instead of in-order camera trajectoriesGenRC · ScanNet (3% input)PSNR: 12.9 -> 12.7No clear effect
shuffle camera trajectories for RGBD2RGBD2 · ScanNet (3% input)depth MSE: 0.72 -> 1.72Hurt

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