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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add image features to echo-only prediction (ablation) | Simple-concatenation depth model · Replica | RMSE: 0.995 -> 0.673 | Improved |
| add material features to echo-only prediction (ablation) | Simple-concatenation depth model · Replica | RMSE: 0.995 -> 0.523 | Improved |
| add material features to echo + image prediction (ablation) | Simple-concatenation depth model · Replica | RMSE: 0.673 -> 0.491 | Improved |
| use bilinear attention fusion instead of concatenation (ablation) | Audio-visual depth prediction · Replica | RMSE: 0.259 -> 0.249 | Improved |
| use bilinear attention fusion instead of dot-product fusion (ablation) | Audio-visual depth prediction · Replica | RMSE: 0.262 -> 0.249 | Improved |
| add attention-based depth-map weighting instead of direct feature concatenation and decoding (ablation) | VisualEchoes · Replica | RMSE: 0.346 -> 0.259 | Improved |
| use material-aware bilinear attention fusion rather than VisualEchoes fusion | Audio-visual depth prediction · Replica | RMSE: 0.346 -> 0.249 | Improved |
| use material-aware bilinear attention fusion rather than VisualEchoes fusion | Audio-visual depth prediction · Matterport3D | RMSE: 0.998 -> 0.950 | Improved |
| reduce image resolution to 1/8x while retaining echo input | Proposed Method · Replica | RMSE: 0.281 vs. 0.374 | Improved |
| reduce image resolution to 1/32x while retaining echo input | Proposed Method vs VisualEchoes · Replica | RMSE: 0.446 cf. 0.593 | Improved |
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.
- VisualEchoes — VisualEchoes: Spatial Image Representation Learning through Echolocation (ECCV 2020) · better on 2 of 2 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
- Stereo Depth Estimation with Echoes (ECCV 2022 · similarity 0.92)
- EchoDiffusion: Waveform Conditioned Diffusion Models for Echo-Based Depth Estimation (AAAI 2025 · similarity 0.87)
- Towards Multimodal Depth Estimation From Light Fields (CVPR 2022 · similarity 0.85)
- Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo (CVPR 2022 · similarity 0.85)
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · similarity 0.85)
- DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching (AAAI 2025 · similarity 0.84)
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.
