AI Paper Atlas

Research map / 3D vision / 3D generation

DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors

Zizheng Yan, Jiapeng Zhou, Fanpeng Meng, Yushuang Wu, Lingteng Qiu, Zisheng Ye, Shuguang Cui, Guanying CHEN, Xiaoguang Han

ECCV 2024 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 7 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
disentangle a multi-object NeRF with DreamDissector instead of negative promptingmulti-object text-to-3D NeRF · Multi-object text-to-3D promptsCLIP score (CLIP-B-16): 0.299 -> 0.316Improved
disentangle with DreamDissector instead of the composition baselinemulti-object text-to-3D NeRF · Multi-object text-to-3D promptsCLIP score (CLIP-L-14): 0.234 -> 0.270Improved
add Deep Concept Mining to Category Score Distillation Sampling (ablation)NeCF disentanglement · concept-gap cases (frog on water lily, beagle, octopus)qualitative disentanglementImproved
use DCM instead of SA3D for disentanglement (ablation)NeCF disentanglement · occlusion cases (beagle, octopus)qualitative disentanglementImproved
use DCM-finetuned diffusion for DMTet refinement instead of original Stable Diffusion (ablation)DMTet refinement · stack of pancakes (qualitative)artifact removalImproved
remove masked attention loss, first stage training or second stage training from DCM (ablation)Deep Concept Mining · baby bunny on pancakes (qualitative)concept separationHurt
apply TEXTure per disentangled object instead of the whole multi-object meshTEXTure · texture editing casesqualitative texture qualityImproved
disentangle objects in very close contact such as body and clothingDreamDissector · failure casesqualitative disentanglementHurt

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