Bi3D: Stereo Depth Estimation via Binary Classifications
This addresses the need for faster depth estimation in applications like autonomous navigation, offering a flexible trade-off between accuracy and latency, though it is incremental as it builds on existing stereo methods.
The paper tackles stereo depth estimation by introducing Bi3D, a method that uses binary classifications to trade accuracy for lower latency, enabling object detection closer than a given distance in a few milliseconds or depth estimation with coarse quantization, while achieving performance close to state-of-the-art for standard continuous depth.
Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy for lower latency. We present Bi3D, a method that estimates depth via a series of binary classifications. Rather than testing if objects are at a particular depth $D$, as existing stereo methods do, it classifies them as being closer or farther than $D$. This property offers a powerful mechanism to balance accuracy and latency. Given a strict time budget, Bi3D can detect objects closer than a given distance in as little as a few milliseconds, or estimate depth with arbitrarily coarse quantization, with complexity linear with the number of quantization levels. Bi3D can also use the allotted quantization levels to get continuous depth, but in a specific depth range. For standard stereo (i.e., continuous depth on the whole range), our method is close to or on par with state-of-the-art, finely tuned stereo methods.