AI Paper Atlas

Research map / 3D vision / 3D generation

MVDD: Multi-View Depth Diffusion Models

Zhen Wang, Qiangeng Xu, Feitong Tan, Menglei Chai, Shichen Liu, Rohit Pandey, Sean Fanello, Achuta Kadambi, Yinda Zhang

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 10 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 epipolar line segment cross attention across views (ablation)MVDD · ShapeNet Chair1-NNA (EMD): 90.00 -> 59.65Improved
add depth concatenation to attention values (ablation)MVDD · ShapeNet Chair1-NNA (EMD): 59.65 -> 59.00Improved
add cross attention thresholding (ablation)MVDD · ShapeNet Chair1-NNA (EMD): 59.00 -> 57.75Improved
add denoising depth fusion (ablation)MVDD · ShapeNet Chair1-NNA (EMD): 57.75 -> 54.51Improved
increase number of points by upsampling LION output versus MVDD native dense pointsLION vs MVDD · ShapeNet Chair1-NNAHurt
use MVDD as 3D prior (SDS regularization) in GAN inversionEG3D PTI inversion · FFHQ 3D GAN inversionqualitative novel-view qualityImproved

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