Shape estimation in natural illumination

Johnson, Micah K.; Adelson, Edward H.

doi:10.1109/cvpr.2011.5995510

Cited by 145 publications

(103 citation statements)

References 25 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…Our work is most similar to recent work on shape recovery in natural illumination by Huang and Smith [9], and Johnson and Adelson [11]. The primary distinction is that our work allows for objects of arbitrary isotropic BRDF whereas these authors have assumed a Lambertian material.…”

Section: Related Worksupporting

confidence: 66%

“…When the reflectance map is parametric, as is the case for Lambertian materials in typical lighting environments, such a search can be done using a gradient descent method [9,11]. In our case, the entropy of the reflectance map varies based on the illumination environment and the reflectance making some regions more difficult to estimate than others.…”

Section: The Image Formation Process In An Ideal Worldmentioning

confidence: 99%

“…The relative root-meansquared error for the recovered BRDFs ranges from 0.54 to 3.02 though the median value is 1.1. In order to directly compare with the work of Johnson and Adelson [11], we have also briefly tested our method assuming the ground-truth reflectance map is known. In this case we achieve an median angular errors consistently below 15…”

Section: Synthetic Imagesmentioning

confidence: 99%

“…Each row of the figure shows 5 of the 10 different shapes from the Blobby Shapes database [11]. Each of these 10 shapes is rendered under 6 different publicly-available realworld illumination environments [5] with each of 10 different real-world measured BRDFs which were chosen from the MERL database [14] to span a wide variety of reflectances.…”

Section: Synthetic Imagesmentioning

confidence: 99%

See 3 more Smart Citations

Shape and Reflectance from Natural Illumination

Oxholm

Nishino

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. We introduce a method to jointly estimate the BRDF and geometry of an object from a single image under known, but uncontrolled, natural illumination. We show that this previously unexplored problem becomes tractable when one exploits the orientation clues embedded in the lighting environment. Intuitively, unique regions in the lighting environment act analogously to the point light sources of traditional photometric stereo; they strongly constrain the orientation of the surface patches that reflect them. The reflectance, which acts as a bandpass filter on the lighting environment, determines the necessary scale of such regions. Accurate reflectance estimation, however, relies on accurate surface orientation information. Thus, these two factors must be estimated jointly. To do so, we derive a probabilistic formulation and introduce priors to address situations where the reflectance and lighting environment do not sufficiently constrain the geometry of the object. Through extensive experimentation we show what this space looks like, and offer insights into what problems become solvable in various categories of real-world natural illumination environments.

show abstract

Section: Related Worksupporting

confidence: 66%

Section: The Image Formation Process In An Ideal Worldmentioning

confidence: 99%

Section: Synthetic Imagesmentioning

confidence: 99%

Section: Synthetic Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Shape and Reflectance from Natural Illumination

Oxholm

Nishino

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

show abstract

“…We have attempted to expand the robot's ability to estimate object hardness with an optical based touch sensor GelSight [5], [6]. The sensor takes high-resolution tactile images of the contact geometry and deformation distribution.…”

Section: Inroductionmentioning

confidence: 99%

Estimating object hardness with a GelSight touch sensor

Yuan

Srinivasan

Adelson³

2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Abstract-Hardness sensing is a valuable capability for a robot touch sensor. We describe a novel method of hardness sensing that does not require accurate control of contact conditions. A GelSight sensor is a tactile sensor that provides high resolution tactile images, which enables a robot to infer object properties such as geometry and fine texture, as well as contact force and slip conditions. The sensor is pressed on silicone samples by a human or a robot and we measure the sample hardness only with data from the sensor, without a separate force sensor and without precise knowledge of the contact trajectory. We describe the features that show object hardness. For hemispherical objects, we develop a model to measure the sample hardness, and the estimation error is about 4% in the range of 8 Shore 00 to 45 Shore A. With this technology, a robot is able to more easily infer the hardness of the touched objects, thereby improving its object recognition as well as manipulation strategy.

show abstract

PS-FCN: A Flexible Learning Framework for Photometric Stereo

Chen

Han

Wong

2018

Lecture Notes in Computer Science

129

189

View full text Add to dashboard Cite

This paper addresses the problem of photometric stereo for non-Lambertian surfaces. Existing approaches often adopt simplified reflectance models to make the problem more tractable, but this greatly hinders their applications on real-world objects. In this paper, we propose a deep fully convolutional network, called PS-FCN, that takes an arbitrary number of images of a static object captured under different light directions with a fixed camera as input, and predicts a normal map of the object in a fast feed-forward pass. Unlike the recently proposed learning based method, PS-FCN does not require a pre-defined set of light directions during training and testing, and can handle multiple images and light directions in an order-agnostic manner. Although we train PS-FCN on synthetic data, it can generalize well on real datasets. We further show that PS-FCN can be easily extended to handle the problem of uncalibrated photometric stereo. Extensive experiments on public real datasets show that PS-FCN outperforms existing approaches in calibrated photometric stereo, and promising results are achieved in uncalibrated scenario, clearly demonstrating its effectiveness.

show abstract

Shape estimation in natural illumination

Cited by 145 publications

References 25 publications

Shape and Reflectance from Natural Illumination

Shape and Reflectance from Natural Illumination

Estimating object hardness with a GelSight touch sensor

PS-FCN: A Flexible Learning Framework for Photometric Stereo

Contact Info

Product

Resources

About