GAMES Webinar 2017-18期（Siggraph 2017论文报告） | 章睿嘉（University of California, Berkeley, USA），朱晨阳（Simon Fraser University, Canada）
【GAMES Webinar 2017-18期（Siggraph 2017论文报告）】
报告嘉宾1：章睿嘉（Richard Zhang )，University of California，Berkeley，USA
报告时间：2017年10月19日（星期四）晚20:00 – 20:45（北京时间）
报告题目：Cross-Channel Visual Prediction
Given a grayscale photograph as input, we attack the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We leverage big data and deep networks to develop (a) a fully automatic approach that produces vibrant and realistic colorizations and (b) a user-guided approach which also incorporates sparse, local user “hints” to an output colorization with a CNN. We validate our method by using real human judges. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. We show that the generalization of the idea, entitled “split-brain autoencoders”, is a straightforward modification of the traditional autoencoder. This method achieves state-of-the-art performance on several large-scale transfer learning benchmarks.
Richard Zhang is a PhD candidate in the EECS department at University of California, Berkeley, advised by Professor Alexei A. Efros. He obtained his Bachelor of Science and Master of Engineering degrees from Cornell University in Electrical and Computer Engineering (ECE). His research interests are in Computer Vision, Machine Learning, Deep Learning, and Sensor Fusion. He is a recipient of a 2017 Adobe Research Fellowship award. Homepage: http://richzhang.github.io/
报告嘉宾2：朱晨阳，Simon Fraser University，Canada
报告时间：2017年10月19日（星期四）晚20:45 – 21:30（北京时间）
报告题目：Deformation-Driven Shape Correspondence via Shape Recognition
Many approaches to shape comparison and recognition start by establishing a shape correspondence. We “turn the table” and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we develop computes a fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only recognizes shapes globally. This is made possible by casting the part correspondence problem in a deformation-driven framework and relying on a data-driven “deformation energy” which rates visual similarity between deformed shapes and models from a shape repository. Our basic premise is that if a correspondence between two chairs (or airplanes, bicycles, etc.) is correct, then a reasonable deformation between the two chairs anchored on the correspondence ought to produce plausible, “chair-like” in-between shapes.
Given two 3D shapes belonging to the same category, we perform a top-down, hierarchical search for part correspondences. For a candidate correspondence at each level of the search hierarchy, we deform one input shape into the other, while respecting the correspondence, and rate the correspondence based on how well the resulting deformed shapes resemble other shapes from ShapeNet belonging to the same category as the inputs. The resemblance, i.e., plausibility, is measured by comparing multi-view depth images over category-specific features learned for the various shape categories. We demonstrate clear improvements over state-of-the-art approaches through tests covering extensive sets of man-made models with rich geometric and topological variations
朱晨阳， Simon Fraser University在读博士生，2011年本科毕业于国防科技大学，2014年研究生毕业于国防科技大学。目前的研究方向为几何形状分析。主页：http://www.sfu.ca/~cza68/
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；