2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper ID3D-3.5
Paper Title STAD: STABLE VIDEO DEPTH ESTIMATION
Authors Hyunmin Lee, Jaesik Park, Pohang University of Science and Technology, Republic of Korea
Session3D-3: Stereoscopic and multiview processing
LocationArea J
Session Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Poster
Topic Three-Dimensional Image and Video Processing: Stereoscopic and multiview processing and display
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract We present a method for estimating temporally stable depth video from a sequence of images. We extend the prior work aimed at video depth estimation, Neural-RGBD, which proposed to use temporal information by accumulating a depth probability volume over time. We propose three simple yet effective ideas to gain improvement: (1) temporal attention module to select and propagate only the meaningful temporal information, (2) geometric warping operation to warp neighbor features in the way of preserving geometry cues, and (3) scale-invariant loss to relieve the inherent scale ambiguity problem in monocular depth estimation task. We demonstrate the efficiency of proposed ideas by comparing our proposed network STAD with the state-of-the-arts. Moreover, we compare STAD with its per-frame network STAD-frame to show the importance of utilizing temporal information. The experimental results show that STAD significantly improved the baseline accuracy without a large parameter increase.