Projects

Summary

A typical class project might be implementing and evaluating an algorithm from a research paper. The choice of projects can be very open-ended; ideally you can incorporate their own research. But your class project must be about new things you have done this semester; you can't use results you have developed in previous semesters. People can work individually or in teams of two.

Project grading

Recall the project is worth half the class grade.

Project Proposal (due May 18th 11 am in EEE dropbox) 10% of project grade
The proposal should include a title, roughly 2 paragraphs describing the project idea, and a list of 1-3 relevant papers. If you will be collecting your own images, describe any special experimental procedure (restriction of illumination conditions, the use of projectors, etc.). If we do not have the facilities here, you may be able to email authors of a paper for their collected data. If you will be using a standard image dataset, include a pointer to it.

Final Writeup (due June 9th, 1:30 pm in EEE dropbox) 60% of project grade
You must prepare a writeup using the given CVPR latex format. There is a strict page limit of 8 pages including references. A single writeup is required per project.

Presentation (June 9th, 1:30-3:30 pm) 30% of project grade.
You must prepare a presentation with a strict time limit of 10 minutes.

Project ideas

Again, you are strongly encouraged to find a project aligned with their own research interests. Here are some pointers to interesting papers in the context of the material we have talked about.

Research papers from ECCV 2008
Research papers from CVPR 2008
Research papers from SIGGRAPH 2008

Research papers from the Visual Geometry Group at Oxford
Research papers from the CAVE Lab at Columbia
Research papers from Wojciech Matusik (with many BRDF/reflectance datasets)
Research papers from Richard Hartley
Research papers from Steve Seitz
Research papers from Ravi Ramamoorthi
Research papers from Srinivas Narasimhan
Research papers from Todd Zickler

Range image database
Photometric stereo" dataset

Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration Chandraker et. al., ICCV 07.

Time-Varying BRDFs Bo Sun, Kalyan Sunkavalli, Ravi Ramamoorthi, Peter Belhumeur, and Shree Nayar, TOG 2007.

Spacetime Faces: High-Resolution Capture for Modeling and Animation Zhang et al. SIGGRAPH 04.

Where do people draw lines? Cole et al, SIGGRAPH 2008 (with data).

A signal processing framework for reflections R. Ramamoorthi and P. Hanrahan, TOG 04.

Detecting Specular Surfaces on Natural Images A. DelPozo and S. Savarese, CVPR 07.

Combining Cues: Shape from Shading and Texture R. White and D.A. Forsyth, CVPR 06.

Local Shape from Mirror Reflections S. Savarese, M. Chen, and P. Perona IJCV 05.

The Bas-Relief Ambiguity P. Belhumeur, D. Kriegman, and A. Yuille IJCV 99.

Color subspaces as Photometric Invariants T. Zickler et al. IJCV, to appear.

Helholtz Stereopsis:Exploiting Reciprocity for Surface Reconstruction, T. Zickler, P. Belhumeur and D. Kriegman.

What Do the Sun and the Sky Tell Us About the Camera? J. Lalonde and S. Narasimhan and A. Efros, ECCV 08 (with data)

Vision and the Atmosphere S. Narasimhan and S. Nayar, IJCV 02 (with data )

A Perception-Based Color Space for Illumination-Invariant Image Processing H. Chong, S. Gortler and T. Zickler, SIGRAPH 08.

A projective framework for radiometric image analysis P. Tan and T. Zickler, CVPR 09.

Fast Separation of Direct and Global Components of a Scene using High Frequency Illumination Nayar et al. SIGGRAPH 2006.

Skin Texture Modeling Cula et al, IJCV 05 (with data).

Using Specularities for Recognition Osadchy et al, ICCV 03.

Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo Zhang et al. ICCV 03.

Photo tourism: Exploring photo collections in 3D Snavely et al. SIGGRAPH 06 (with data and code).

Bundle Adjustment - A Modern Synthesis Bill Triggs, Vision Algorithms 99.