|09:00|| Invited Talk: Paul Newman (University of Oxford)
“Large Scale, Long Term Vision based localisation in all weathers for all places”
|09:35|| Invited Talk: Bill Freeman (MIT)
“Computer vision with the moon and the stars”
|10:30|| Invited Talk: Judy Hoffman (Facebook AI)
“Generalizing models to a diverse world” [ Slides ]
|11:05|| Poster Session: All accepted papers and abstracts
“The poster setup instructions and all papers can be found below this table”
|13:45|| Invited Talk: Vishal M. Patel (Johns Hopkins University)
“Nighttime and Low-Light Face Recognition”
|14:20|| Oral Presentations
14:20: Mario Bijelic (Daimler AG & Ulm University)
“Automotive Sensor Performance in Adverse Weather”
14:32: Tobias Gruber (Daimler AG & Ulm University)
“Gated Imaging for Autonomous Driving in Adverse Weather”
14:44: Jonah Philion (iSee AI)
“FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network”
14:56: Li Ruoteng (NUS)
“Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning”
15:08: Horia Porav (University of Oxford)
“Towards a canonical representation for robot vision under difficult conditions”
|15:30|| Invited Talk: Srinivasa Narasimhan (CMU)
“Smart Illumination for Bad Weather”
|16:05|| Invited Talk: Daniel Cremers (TU Munich)
“Realtime visual SLAM and relocalization for all seasons”
|16:40|| Invited Talk: Oscar Beijbom (nuTonomy)
“3D detection across weathers, conditions, and locations: algorithms and benchmarks”
|17:15|| Panel Discussion:
Panelists: Daniel Cremers, Srinivasa Narasimhan, Paul Newman, Vishal M. Patel
- Poster are for all accepted paper and abstracts;
- Poster boards in Pacific Arena Ballroom (main convention center);
- Poster number: #93:#106; Feel free to choose an available board in this number range.
- Note that posters cannot be put up prior to the session (11:05–12:15) and need to be removed following the session. This means, we put up our posters at 11:05, and we remove our posters after our session (removing after lunch break should be okay).
- Riccardo Volpi and Vittorio Murino. Model Vulnerability to Distributional Shifts over Image Transformation Sets.
- Yibiao Zhao and Jonah Philion. FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network.
- Mario Bijelic, Tobias Gruber, Werner Ritter, and Klaus Dietmayer. Automotive Sensor Performance in Adverse Weather.
- Tobias Gruber, Mario Bijelic, Werner Ritter, and Klaus Dietmayer. Gated Imaging for Autonomous Driving in Adverse Weather.
- Ruoteng Li, Loong-Fah Cheong, and Robby T. Tan. Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning.
Accepted Short Papers
- Han-Kai Hsu, Wei-Chih Hung, Hung-Yu Tseng, Chun-Han Yao, Yi-Hsuan Tsai, Maneesh Singh, and Ming-Hsuan Yang. Progressive Domain Adaptation for Object Detection.
- Wayne Treible, Philip Saponaro, Yi Liu, Agnijit Das Gupta, Vinit Veerendraveer, Scott Sorensen, and Chandra Kambhamettu. CATS 2: Color And Thermal Stereo Scenes with Semantic Labels.
- Horia Porav, Valentina Musat, and Paul Newman. Reducing Steganography In Cycle-consistency GANs.
- Amitangshu Mukherjee, Ameya Joshi, Soumik Sarkar, and Chinmay Hegde. Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models.
Accepted Normal Papers
- Mario Bijelic, Paula Kysela, Tobias Gruber, Werner Ritter, Klaus Dietmayer. Recovering the Unseen: Benchmarking the Generalization of Enhancement Methods to RealWorld Data in Heavy Fog.
- Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, and Erik Learned-Miller. Automatic adaptation of object detectors to new domains using self-training.
- Guisik Kim, Jinhee Park, Suhyeon Ha, and Junseok Kwon. Bidirectional Deep Residual learning for Haze Removal.
- Joakim Bruslund Haurum, Chris H. Bahnsen, and Thomas B. Moeslund. Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras.
- Luan Tran, Kihyuk Sohn, Xiang Yu, Xiaoming Liu, and Manmohan Chandraker. Gotta Adapt ’Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild . Supplementary Material.
- Samin Khan, Buu Phan, Rick Salay, and Krzysztof Czarnecki. ProcSy: Procedural Synthetic Dataset Generation Towards Influence Factor Studies Of Semantic Segmentation Networks.