paper-with-me

Papers

Learning about Canonical Views from Internet Image Collections

2012-12-01 · NeurIPS 2012 12 · Elad Mezuman, Yair Weiss

Although human object recognition is supposedly robust to viewpoint, much research on human perception indicates that there is a preferred or “canonical” view of objects. This phenomenon was discovered more than 30 years ago but the canonical view of only a small number of categories has been validated experimentally. Moreover, the explanation for why humans prefer the canonical view over other views remains elusive. In this paper we ask: Can we use Internet image collections to learn more about canonical views? We start by manually finding the most common view in the results returned by Internet search engines when queried with the objects used in psychophysical experiments. Our results clearly show that the most likely view in the search engine corresponds to the same view preferred by human subjects in experiments. We also present a simple method to find the most likely view in an image collection and apply it to hundreds of categories. Using the new data we have collected we present strong evidence against the two most prominent formal theories of canonical views and provide novel constraints for new theories.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Similar Papers 제목 키워드 기반

NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections

2020-08-05 · CVPR 2021 1 · Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron 외

We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a mul…

NeRF

Extreme Rotation Estimation in the Wild

2024-11-11 · CVPR 2025 1 · Hana Bezalel, Dotan Ankri, Ruojin Cai, Hadar Averbuch-Elor

We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limited or non-overlapping field of views. P…

3D Reconstruction

Shelf-Supervised Mesh Prediction in the Wild

2021-02-11 · CVPR 2021 1 · Yufei Ye, Shubham Tulsiani, Abhinav Gupta

We aim to infer 3D shape and pose of object from a single image and propose a learning-based approach that can train from unstructured image collections, supervised by only segmentation outputs from off-the-shelf recogni…

Prediction

ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

2022-01-19 · CVPR 2022 1 · Rahul Sajnani, Adrien Poulenard, Jivitesh Jain, Radhika Dua 외

Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-t…

3D Canonicalization3D Geometry Perception3D Part Segmentation3D Pose Estimation+1

3D Congealing: 3D-Aware Image Alignment in the Wild

2024-04-02 · Yunzhi Zhang, Zizhang Li, Amit Raj, Andreas Engelhardt 외

We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images capturing semantically similar objects. Given a collection of unlabeled Internet images, our goal is to associate the shared semantic parts fr…

Pose Estimation