AI Paper Atlas

Research map / 3D vision / 3D generation

Vista3D: unravel the 3d darkside of a single image

Qiuhong Shen, Xingyi Yang, Michael Bi Mi, Xinchao Wang

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 1 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 second diffusion prior (Stable Diffusion) with angular score composition (Vista3D-L versus Vista3D-S) (ablation)Vista3D · RealFusion datasetCLIP-Similarity: 0.831 -> 0.868Improved
add angular prior composition (Vista3D-L versus Vista3D-S) (ablation)Vista3D · GSO (30 objects)PSNR: 25.42 -> 26.31Improved
use naive fixed weight 1/40 on the 2D diffusion SDS term instead of angular composition (ablation)Vista3D-L · qualitative examplesback-view textureHurt
remove angular score composition (ablation)Vista3D-L · qualitative examplesfront-view consistency with referenceHurt
skip coarse Gaussian-splatting stage and learn isosurface geometry directly (ablation)Vista3D · qualitative examplesgeometry qualityHurt
use two disentangled hash encodings (forward and back) instead of one (ablation)Vista3D · qualitative examplestexture artifactsImproved
use Top-K gradient-based densification instead of naive gradient threshold (ablation)Vista3D coarse stage · qualitative examplesgeometry qualityImproved
add transmittance regularization to the coarse stage (ablation)Vista3D coarse stage · qualitative examplesmesh watertightnessImproved
add scale regularization to the coarse stage (ablation)Vista3D coarse stage · qualitative examplesgeometry detailImproved
use Vista3D-S instead of Magic123 for image-to-3Dimage-to-3D generation · RealFusion datasetCLIP-Similarity and time: 0.802 -> 0.831Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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