AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Beyond Image to Depth: Improving Depth Prediction Using Echoes

Kranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

CVPR 2021 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 41 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add image features to echo-only prediction (ablation)Simple-concatenation depth model · ReplicaRMSE: 0.995 -> 0.673Improved
add material features to echo-only prediction (ablation)Simple-concatenation depth model · ReplicaRMSE: 0.995 -> 0.523Improved
add material features to echo + image prediction (ablation)Simple-concatenation depth model · ReplicaRMSE: 0.673 -> 0.491Improved
use bilinear attention fusion instead of concatenation (ablation)Audio-visual depth prediction · ReplicaRMSE: 0.259 -> 0.249Improved
use bilinear attention fusion instead of dot-product fusion (ablation)Audio-visual depth prediction · ReplicaRMSE: 0.262 -> 0.249Improved
add attention-based depth-map weighting instead of direct feature concatenation and decoding (ablation)VisualEchoes · ReplicaRMSE: 0.346 -> 0.259Improved
use material-aware bilinear attention fusion rather than VisualEchoes fusionAudio-visual depth prediction · ReplicaRMSE: 0.346 -> 0.249Improved
use material-aware bilinear attention fusion rather than VisualEchoes fusionAudio-visual depth prediction · Matterport3DRMSE: 0.998 -> 0.950Improved
reduce image resolution to 1/8x while retaining echo inputProposed Method · ReplicaRMSE: 0.281 vs. 0.374Improved
reduce image resolution to 1/32x while retaining echo inputProposed Method vs VisualEchoes · ReplicaRMSE: 0.446 cf. 0.593Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy