AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving

YIBO LIU, Zheyuan Yang, Guile Wu, Yuan Ren, Kejian Lin, Liu Bingbing, Yang Liu, JINJUN SHAN

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 12 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 multi-expert DMs instead of one single DM for 16 views (ablation)VQA-Diff structure generation · BMW X5 structure generationFID: 192.55 -> 122.91Improved
train the single DM for 100 epochs instead of 50 (ablation)Single DM baseline · BMW X5 structure generationFID: 192.55 -> 189.04No clear effect
reduce views per single DM image from 16 to 9 (ablation)Single DM baseline · BMW X5 structure generationFID: 192.55 -> 150.31Improved
add ControlNet appearance generation (ablation)VQA-Diff · WaymoFID: 186.98 -> 163.40Improved
add ControlNet to NFI trained on ShapeNet (ablation)NFI · WaymoFID: 428.35 -> 267.47Improved
use VQA-derived prompt for geometry instead of NFI when both trained on ShapeNet (ablation)VQA-Diff · WaymoFID: 267.47 -> 186.98Improved
apply VQA-Diff to teddy bear instead of vehiclesVQA-Diff · Generic objects (qualitative)structure consistencyHurt

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