Talking Papers Podcast

Talking Papers Podcast

A podcast by researchers for researchers. This podcast aims to be a new medium for disseminating research. In each episode I talk to the main author of an academic paper in the field of computer vision, machine learning, artificial intelligence, graphics and everything in between. Each episode is structured like a paper and includes a TL;DR (abstract), related work, approach, results, conclusions and a future work section. It also includes the bonus "what did reviewer 2 say" section where authors share their experience in the peer review process. Enjoy!

Episodes

May 6, 2022 31 min

 In this episode of the Talking Papers Podcast, I hosted Dejan Azinović to chat about his paper "Neural RGB-D Surface Reconstruction”, published in CVPR 2022.

In this paper, they take on the task of RGBD surface reconstruction by using novel view synthesis.  They incorporate depth measurements into the radiance field formulation by learning a neural network that stores a truncated signed distance field. This formulation is part...

Share
Mark as Played

In this episode of the Talking Papers Podcast, I hosted Yuliang Xiu to chat about his paper "ICON: Implicit Clothed humans Obtained from Normals”, published in CVPR 2022. SMPL(-X) body model to infer clothed humans (conditioned on the normals).  Additionally, they propose an inference-time feedback loop that alternates between refining the body's normals and the shape. 

PAPER TITLE 
"ICON: Implicit Clothed humans Obtained...

Share
Mark as Played
March 28, 2022 37 min

In this episode of the Talking Papers Podcast, I hosted Itai Lang to chat about his paper "SampleNet: Differentiable Point Cloud Sampling”, published in CVPR 2020. In this paper, they propose a point soft-projection to allow differentiating through the sampling operation and enable learning task-specific point sampling. Combined with their regularization and task-specific losses, they can reduce the number of points to 3% of th...

Share
Mark as Played

In this episode of the Talking Papers Podcast, I hosted Manuel Dahnert to chat about his paper “Panoptic 3D Scene Reconstruction From a Single RGB Image”, published in NeurIPS 2021.  In this paper, they unify the task of reconstruction, semantic segmentation and instance segmentation in 3D from a single RGB image. They propose a holistic approach to lift the 2D features into a 3D grid.  Manuel is a good friend and colleague. We fir...

Share
Mark as Played
February 24, 2022 34 min

In this episode of the Talking Papers Podcast, I hosted Songyou Peng to chat about his paper “Shape As Points: A Differentiable Poisson Solver”, published in NeurIPS 2021. In this paper, they take on the task of surface reconstruction and propose a hybrid representation that unifies explicit and implicit representation in addition to a differentiable solver for the classic Poisson surface reconstruction. I have been following Songy...

Share
Mark as Played
February 17, 2022 22 min

PAPER TITLE:
"VLN BERT:  A Recurrent Vision-and-Language BERT for Navigation"

AUTHORS: 
Yicong Hong, Qi Wu, Yuankai Qi, Cristian Rodriguez-Opazo, Stephen Gould

ABSTRACT:
Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language (V&L) BERT. However, its application for the task of vision and-language navigation (VLN) remains limited. One reason for this is the difficulty ...

Share
Mark as Played
February 10, 2022 40 min

PAPER TITLE
 Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

AUTHORS

Despoina Paschalidou , Angelos Katharopoulos, Andreas Geiger, Sanja Fidler


ABSTRACT

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to t...

Share
Mark as Played
February 3, 2022 32 min

PAPER TITLE:
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction

AUTHORS: 
Guy Gafni      Justus Thies      Michael Zollhöfer     Matthias Nießner   

Project page: https://gafniguy.github.io/4D-Facial-Avatars/

CODE:
💻https://github.com/gafniguy/4D-Facial-Avatars

ABSTRACT:
We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstruct...

Share
Mark as Played
January 20, 2022 30 min

PAPER TITLE:
"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders"

AUTHORS:
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes

ABSTRACT:
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the salie...

Share
Mark as Played

PAPER TITLE:
"Deep Declarative Networks: a new hope"

AUTHORS:
Stephen Gould, Richard Hartley, Dylan Campbell

ABSTRACT:
We explore a new class of end-to-end learnable models wherein data processing nodes (or network layers) are defined in terms of desired behaviour rather than an explicit forward function. Specifically, the forward function is implicitly defined as the solution to a mathematical optimization problem. Consistent w...

Share
Mark as Played
January 5, 2022 27 min

Paper title:
"DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video"

Authors:  Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen Gould

Abstract:
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and end of the relevant ...

Share
Mark as Played

Popular Podcasts

    Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations.

    Crime Junkie

    If you can never get enough true crime... Congratulations, you’ve found your people.

    Morbid: A True Crime Podcast

    It’s a lighthearted nightmare in here, weirdos! Morbid is a true crime, creepy history and all things spooky podcast hosted by an autopsy technician and a hairstylist. Join us for a heavy dose of research with a dash of comedy thrown in for flavor.

    Stuff You Should Know

    If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks then look no further. Josh and Chuck have you covered.

    Sympathy Pains

    Hosted by Laura Beil (Dr. Death, Bad Batch), Sympathy Pains is a six-part series from Neon Hum Media and iHeartRadio. For 20 years, Sarah Delashmit told people around her that she had cancer, muscular dystrophy, and other illnesses. She used a wheelchair and posted selfies from a hospital bed. She told friends and coworkers she was trapped in abusive relationships, or that she was the mother of children who had died. It was all a con. Sympathy was both her great need and her powerful weapon. But unlike most scams, she didn’t want people’s money. She was after something far more valuable.

Advertise With Us

For You

    Music, radio and podcasts, all free. Listen online or download the iHeart App.

    Connect

    © 2022 iHeartMedia, Inc.