Source-free Depth for Object Pop-out

by   Zongwei Wu, et al.

Depth cues are known to be useful for visual perception. However, direct measurement of depth is often impracticable. Fortunately, though, modern learning-based methods offer promising depth maps by inference in the wild. In this work, we adapt such depth inference models for object segmentation using the objects' “pop-out” prior in 3D. The “pop-out” is a simple composition prior that assumes objects reside on the background surface. Such compositional prior allows us to reason about objects in the 3D space. More specifically, we adapt the inferred depth maps such that objects can be localized using only 3D information. Such separation, however, requires knowledge about contact surface which we learn using the weak supervision of the segmentation mask. Our intermediate representation of contact surface, and thereby reasoning about objects purely in 3D, allows us to better transfer the depth knowledge into semantics. The proposed adaptation method uses only the depth model without needing the source data used for training, making the learning process efficient and practical. Our experiments on eight datasets of two challenging tasks, namely camouflaged object detection and salient object detection, consistently demonstrate the benefit of our method in terms of both performance and generalizability.


page 3

page 7

page 8


Depth-Guided Camouflaged Object Detection

Camouflaged object detection (COD) aims to segment camouflaged objects h...

SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection

RGB-D salient object detection (SOD) has been in the spotlight recently ...

Object-Centric Image Generation with Factored Depths, Locations, and Appearances

We present a generative model of images that explicitly reasons over the...

Region Graph Based Method for Multi-Object Detection and Tracking using Depth Cameras

In this paper, we propose a multi-object detection and tracking method u...

Counterfactual Depth from a Single RGB Image

We describe a method that predicts, from a single RGB image, a depth map...

Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

Training object detection models usually requires instance-level annotat...

Contact Area Detector using Cross View Projection Consistency for COVID-19 Projects

The ability to determine what parts of objects and surfaces people touch...

Please sign up or login with your details

Forgot password? Click here to reset