To a depth camera, a glass wall is basically empty space. This model fills it back in.
Summary
A model is proposed to fill in missing depth data from depth cameras when encountering transparent surfaces like glass walls, addressing a common sensor limitation.
Similar Articles
@heyshrutimishra: Nobody talks about this but every robot on the market is blind to glass. Put a mirror in front of it. A glass bottle. I…
LingBot-Depth 2.0, trained on 150M samples, solves the longstanding problem of robots being blind to glass and transparent objects, achieving top performance on 12/16 depth benchmarks and halving depth error. Ant Group used it to significantly improve their robots' perception.
One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
Introduces MultiDepth-3k, a benchmark to evaluate depth-layer preferences in monocular depth foundation models, and shows Laplacian Visual Prompting can alter reported depth layers, suggesting complementary geometric hypotheses exist across models.
Unified Panoramic Geometry Estimation via Multi-View Foundation Models
PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.
αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
αDepth introduces a layered representation with Circular Alpha Representation (CAR) to address soft boundary challenges in stereo conversion, achieving state-of-the-art performance without manual guidance.
Masked depth modeling with sensor-validity masking: reports best RMSE on 7 of 8 masked/sparse depth benchmarks, plus a controlled encoder-init study[R]
This paper proposes masked depth modeling with sensor-validity masking, achieving best RMSE on 7 out of 8 masked/sparse depth benchmarks, with a controlled encoder-init study.