Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.02552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913180656074752 |
|---|---|
| author | Bian, Siyuan Xu, Congrong Gao, Jun |
| author_facet | Bian, Siyuan Xu, Congrong Gao, Jun |
| contents | Despite advances in depth estimation, flying points remain a persistent failure mode: near object boundaries, depth estimators often predict spurious 3D points in the empty space between foreground and background surfaces. We trace this artifact to a standard modeling choice: assigning each pixel a single depth hypothesis. At boundaries, a pixel can straddle a foreground and a background surface, so its true depth is ambiguous between the two. A model that predicts a single depth cannot keep both possibilities, so training instead pulls the prediction toward an intermediate depth that lies on neither surface. We address this with MDA, a mixture-density representation that lets the model predict multiple depth hypotheses and their associated probabilities for each pixel. Near boundaries, different hypotheses can align with different surfaces, and the decoded depth is selected from one of these hypotheses rather than placed in the empty space between them. Across different backbones, MDA substantially improves boundary reconstruction and largely removes flying-point artifacts even under severe input blur, while adding negligible runtime overhead. The same mixture-density framework naturally extends to transparent objects, where it predicts multiple depth layers at transparent pixels, and to sky regions, where a dedicated component separates the unbounded sky from finite-depth regions, producing flying-point-free skylines. Project Page: https://biansy000.github.io/mda-site/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02552 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation Bian, Siyuan Xu, Congrong Gao, Jun Computer Vision and Pattern Recognition Artificial Intelligence Despite advances in depth estimation, flying points remain a persistent failure mode: near object boundaries, depth estimators often predict spurious 3D points in the empty space between foreground and background surfaces. We trace this artifact to a standard modeling choice: assigning each pixel a single depth hypothesis. At boundaries, a pixel can straddle a foreground and a background surface, so its true depth is ambiguous between the two. A model that predicts a single depth cannot keep both possibilities, so training instead pulls the prediction toward an intermediate depth that lies on neither surface. We address this with MDA, a mixture-density representation that lets the model predict multiple depth hypotheses and their associated probabilities for each pixel. Near boundaries, different hypotheses can align with different surfaces, and the decoded depth is selected from one of these hypotheses rather than placed in the empty space between them. Across different backbones, MDA substantially improves boundary reconstruction and largely removes flying-point artifacts even under severe input blur, while adding negligible runtime overhead. The same mixture-density framework naturally extends to transparent objects, where it predicts multiple depth layers at transparent pixels, and to sky regions, where a dedicated component separates the unbounded sky from finite-depth regions, producing flying-point-free skylines. Project Page: https://biansy000.github.io/mda-site/. |
| title | Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2606.02552 |