AI Paper Atlas

Research map / 3D vision / 3D generation

Autodecoding Latent 3D Diffusion Models

Evangelos Ntavelis, Aliaksandr Siarohin, Kyle Olszewski, Chaoyang Wang, Luc Van Gool, Sergey Tulyakov

NeurIPS 2023 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 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
Use autodecoder latent diffusion instead of DiffRF3D generation · PhotoShape ChairsFID: 15.95 -> 11.28Improved
Use autodecoder latent diffusion instead of DiffRF3D generation · ABO TablesFID: 27.06 -> 18.44Improved
Replace direct latent sampling with diffusion samplingAutodecoding Latent 3D Diffusion · CelebV-TextFID: 69.21 -> 48.01Improved
Replace direct latent sampling with diffusion samplingAutodecoding Latent 3D Diffusion · MVImgNetFID: 97.51 -> 43.85Improved
Replace direct latent sampling with diffusion samplingAutodecoding Latent 3D Diffusion · ObjaverseFID: 72.76 -> 40.49Improved
Add multi-frame training (ablation)Autodecoder · PhotoShape Chairs reconstructionPSNR: 27.176 -> 27.719Improved
Add multi-frame training (ablation)Autodecoder · PhotoShape Chairs reconstructionLPIPS: 6.855 -> 6.255Improved
Add self-attention (ablation)Autodecoder · PhotoShape Chairs reconstructionPSNR: 27.335 -> 27.719Hurt
Add self-attention (ablation)Autodecoder · PhotoShape Chairs reconstructionLPIPS: 6.738 -> 6.255Hurt
Increase residual-block depth (ablation)Autodecoder · PhotoShape Chairs reconstructionPSNR: 27.24 -> 27.719Improved
Increase residual-block depth (ablation)Autodecoder · PhotoShape Chairs reconstructionLPIPS: 6.924 -> 6.255Improved
Increase embedding length from 64 to 1024 (ablation)Autodecoder · PhotoShape Chairs reconstructionPSNR: 25.985 -> 27.719Improved

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