Research map / 3D vision / Face and shape
Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
tyler bonnen, Stephanie Fu, Yutong Bai, Thomas O', Connell, Yoni Friedman, Josh Tenenbaum, Alexei Efros
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's title only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces a benchmark of human-level shape inference tasks to evaluate whether vision models understand 3D shape.
Problem
Evaluating whether vision models have human-like 3D shape understanding, which existing benchmarks may not measure adequately.
Approach
A benchmark of shape inference tasks designed to match human-level 3D understanding, used to test vision models; the abstract only states the benchmark's purpose.
Closest papers by meaning
- Evaluating Multiview Object Consistency in Humans and Image Models (NeurIPS 2024 · similarity 0.87)
- Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering (NeurIPS 2026 · similarity 0.85)
- Learning to Reconstruct Shapes from Unseen Classes (NeurIPS 2018 · similarity 0.85)
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.85)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.84)
- Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models (NeurIPS 2024 · similarity 0.84)
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.
