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!
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...
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.
"ICON: Implicit Clothed humans Obtained...
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...
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...
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...
"VLN BERT: A Recurrent Vision-and-Language BERT for Navigation"
Yicong Hong, Qi Wu, Yuankai Qi, Cristian Rodriguez-Opazo, Stephen Gould
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 ...
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...
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction
Guy Gafni Justus Thies Michael Zollhöfer Matthias Nießner
Project page: https://gafniguy.github.io/4D-Facial-Avatars/
We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstruct...
"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders"
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes
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...
"Deep Declarative Networks: a new hope"
Stephen Gould, Richard Hartley, Dylan Campbell
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...
"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
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 ...
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations.
If you can never get enough true crime... Congratulations, you’ve found your people.
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.
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.
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.