Learning about Canonical Views from Internet Image Collections
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionSimilar Papers 제목 키워드 기반
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
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…
NeRFExtreme Rotation Estimation in the Wild
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 ReconstructionShelf-Supervised Mesh Prediction in the Wild
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…
PredictionConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
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+13D Congealing: 3D-Aware Image Alignment in the Wild
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