AI Paper Atlas

Research map / 3D vision / 3D generation

DATENeRF: Depth-Aware Text-based Editing of NeRFs

Sara Rojas Martinez, Julien Philip, Kai Zhang, Sai Bi, Fujun Luan, Bernard Ghanem, Kalyan Sunkavalli

ECCV 2024 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 9 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 projection inpainting to depth-conditioned ControlNet editing (ablation)DATENeRF · NeRF text editing (24 edits)CLIP Direction Consistency: 0.6879 -> 0.7069Improved
add projection inpainting to depth-conditioned ControlNet editing (ablation)DATENeRF · NeRF text editing (24 edits)CLIP Text-Image Direction Similarity: 0.1772 -> 0.1866Improved
replace Instruct-Pix2Pix with ControlNet in Instruct-NeRF2NeRFInstruct-NeRF2NeRF · NeRF text editing (24 edits)CLIP Text-Image Direction Similarity: 0.1407 -> 0.1330 (similarity), 0.6349 -> 0.6799 (consistency)Mixed
use projection inpainting with Instruct-Pix2Pix instead of plain Instruct-NeRF2NeRF (ablation)Instruct-NeRF2NeRF · NeRF text editing (24 edits)CLIP Direction Consistency: 0.6349 -> 0.6910Improved
use ControlNet without projection inpainting versus with it (ablation)DATENeRF · NeRF text editing (24 edits)CLIP Direction Consistency: 0.7069 -> 0.6879Hurt
keep reprojected pixels for all 20 denoising steps (N=20) instead of 5 (ablation)projection inpainting · bear scene (qualitative)visual qualityHurt
no projection (N=0), depth-conditioned inpainting only (ablation)projection inpainting · bear scene (qualitative)photometric consistencyHurt
edit all images upfront with projection inpainting instead of Iterative Dataset UpdateDATENeRF · bear scene convergenceimage edits and NeRF iterations to converge: 87 edits and 400 iterations vs 300 edits and 3000 iterations (IN2N)Improved

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