IP Library › Granted Patent US 8,913,105
Granted Patent B2
US 8,913,105 · App. 13/143,296 · Granted Dec 16, 2014

Joint depth estimation

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,913,105
App. No.
13/143,296
Granted
Dec 16, 2014
Kind
B2
Abstract

Various implementations are described. Several implementations relate to joint depth estimation for multiple depth maps. In one implementation, a first-view depth indicator for a location in a first view is estimated, and a second-view depth indicator for a corresponding location in a second view is estimated. The estimating of one or more of the first-view depth indicator and the second-view depth indicator is based on a constraint. The constraint provides a relationship between the first-view depth indicator and the second-view depth indicator for corresponding locations.

Claims (55)

1. A method performed by a video coding system, the method comprising:

estimating a first-view depth indicator for a location in a first view, and

estimating a second-view depth indicator for a corresponding location in a second view, wherein the estimating of the first-view depth indicator and the estimating of the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations,

wherein estimating the first-view depth indicator and the second-view depth indicator comprises:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

2. The method of claim 1 further comprising filling the hole using a depth indicator, for a location neighboring the marked location, that indicates the largest depth among locations neighboring the marked location.

3. An apparatus comprising:

means for estimating a first-view depth indicator for a location in a first view, and means for estimating a second-view depth indicator for a corresponding location in a second view, wherein the estimating of the first-view depth indicator and the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein the means for estimating the first-view depth indicator and the means for estimating the second-view depth indicator are each configured for:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

4. A non-transitory processor readable medium having stored therein instructions for causing a processor to perform at least the following:

estimating a first-view depth indicator for a location in a first view and estimating a second-view depth indicator for a corresponding location in a second view, wherein the estimating of the first-view depth indicator and the estimating of the second-view depth indicator

jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein estimating the first-view depth indicator and the second-view depth indicator comprises:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

5. An apparatus, comprising a processor configured to perform at least the following:

estimating a first-view depth indicator for a location in a first view and estimating a second-view depth indicator for a corresponding location in a second view, wherein the estimating of the first-view depth indicator and the estimating of the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein estimating the first-view depth indicator and the second-view depth indicator comprises:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

6. An apparatus comprising:

a depth estimator for estimating a first-view depth indicator for a location in a first view and a depth estimator for estimating a second-view depth indicator for a corresponding location in a second view, the estimating of the first-view depth indicator and the estimating of the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein the depth estimator for estimating the first-view depth indicator and the depth estimator for estimating the second-view depth indicator are each configured for:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

7. An apparatus comprising:

a depth estimator for estimating a first-view depth indicator for a location in a first view and a depth estimator for estimating a second-view depth indicator for a corresponding location in a second view, wherein the estimating of the first-view depth indicator and the estimating of the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein the depth estimator for estimating the first-view depth indicator and the depth estimator for estimating the second-view depth indicator are each configured for:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold; and

a modulator for modulating a signal that includes an encoding of one or more of the first-view depth indicator or the second-view depth indicator.

8. An apparatus comprising:

a demodulator for demodulating a signal that includes video from a first view and video from a second view; and

a depth estimator for estimating a first-view depth indicator for a location in the first view and a depth estimator for estimating a second-view depth indicator for a corresponding location in the second view, wherein the estimating of the first-view depth indicator and the estimating of the second-view depth indicator jointly satisfy a constraint relating the first-view depth indicator directly with respect to the second-view depth indicator for corresponding locations wherein the depth estimator for estimating the first-view depth indicator and the depth estimator for estimating the second-view depth indicator are each configured for:

determining that the depth indicators have values differing by more than a depth-indicator threshold from the relationship provided by the constraint;

determining a first-view distortion for the first-view depth indicator;

determining a second-view distortion for the second-view depth indicator;

marking the location in the first view as a hole if the first-view distortion is greater than the second-view distortion by a distortion threshold; and

marking the corresponding location in the second view as a hole if the second-view distortion is greater than the first-view distortion by the distortion threshold.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 23, 2018
From: THOMSON LICENSING
To: INTERDIGITAL VC HOLDINGS, INC.
Reel/Frame 047289/0698 →