In conjunction with CVPR 2019
June 17, 2019, 9:00 AM - 5:15 PM
Long Beach Convention Center, Long Beach, CA
Room 101B
In computer vision, scene understanding and modeling encapsulate a diverse set of research problems, ranging from low-level geometric modeling (e.g., SLAM algorithms) to 3D room layout estimation. These tasks are often addressed separately, yielding only a constrained understanding and representation of the underlying scene. In parallel, the popularity of 360° cameras has encouraged the digitization of the real world into augmented and virtual realities, enabling new applications such as virtual social interactions and semantically leveraged augmented reality. This workshop aims to promote comprehensive 3D scene understanding and modeling algorithms that create integrated scene representations (with geometry, appearance, semantics, and perceptual qualities), while utilizing 360° imagery to encourage research on its unique challenges.
The 2019 SUMO Challenge Workshop will bring together computer vision researchers working on 3D scene understanding and modeling for a day of keynote speakers, oral presentations, posters, and panel discussions on the topic. The two primary goals of the workshop are:
Encourage the development of comprehensive 3D scene understanding and modeling algorithms that address the aforementioned problems in a single framework.
Foster research on the unique challenges of generating comprehensive digital representations from 360° imagery.
The workshop is soliciting papers covering various problems related to 3D scene understanding and modeling from RGB and RGB-D imagery. The topics mainly focus on indoor scene modeling and include, but are not limited to:
360° data processing and scene understanding
Object detection
Object localization
Layout estimation
“Stuff” detection and modeling
Instance segmentation
Object completion and 3D reconstruction
Object pose estimation
Generative models
Articulated object modeling
Texture and appearance modeling
Material property estimation
Lighting recognition
The submission deadline has passed.
| Start Time | End Time | Description |
|---|---|---|
| 9:00 | 9:10 | Opening remarks |
| 9:10 | 9:40 |
Keynote: Semantic 3D Understanding of Indoor Environments Matthias Niessner |
| 9:40 | 9:50 | Oral 1: Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction Daeyun Shin, Zhile Ren, Erik B. Sudderth, and Charless Fowlkes |
| 9:50 | 10:00 | Oral 2: Efficient Plane-Based Optimization of Geometry and Texture for Indoor RGB-D Reconstruction (slides, code) Chao Wang and Xiaohu Guo |
| 10:00 | 10:45 | Poster session and coffee break |
| 10:45 | 11:15 | Keynote: Where to Look: Navigating and Compressing 360° Videos Kristen Grauman |
| 11:15 | 11:25 | Oral 3: Convolutions on Spherical Images (slides) Marc C. Eder and Jan-Michael Frahm |
| 11:25 | 11:35 | Oral 4: Kernel Transformer Networks for Compact Spherical Convolution Yu-Chuan Su and Kristen Grauman |
| 11:35 | 12:05 | Keynote: Perceiving Non-rigid Objects in the 3D World Angjoo Kanazawa |
| 12:05 | 1:30 | Lunch |
| 1:30 | 2:00 | Keynote: Sanja Fidler |
| 2:00 | 2:10 | Oral 5: Learning Single-View 3D Reconstruction with Limited Pose Supervision Guandao Yang, Yin Cui, Serge Belongie, and Barath Hariharan |
| 2:10 | 2:20 | Oral 6: Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes (slides) Seongdo Kim and Roberto Manduchi |
| 2:20 | 3:15 | Panel discussion with the keynote speakers |
| 3:15 | 4:00 | Poster session and break |
| 4:00 | 4:30 | Keynote: 3D Objects and 3D Humans Jitendra Malik |
| 4:30 | 5:00 | Keynote: Toward Large-scale Interactive Environments Angel Chang |
| 5:00 | 5:15 | Closing remarks |
