Pith. sign in

REVIEW 4 cited by

Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.04472 v2 pith:EK2TPE5G submitted 2024-12-05 cs.CV

Luca Bartolomei , Fabio Tosi , Matteo Poggi , Stefano Mattoccia This is my paper
classification cs.CV
keywords stereonovelanywhereframeworkmatchingrobustzero-shotachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Stereo Anywhere, a novel stereo-matching framework that combines geometric constraints with robust priors from monocular depth Vision Foundation Models (VFMs). By elegantly coupling these complementary worlds through a dual-branch architecture, we seamlessly integrate stereo matching with learned contextual cues. Following this design, our framework introduces novel cost volume fusion mechanisms that effectively handle critical challenges such as textureless regions, occlusions, and non-Lambertian surfaces. Through our novel optical illusion dataset, MonoTrap, and extensive evaluation across multiple benchmarks, we demonstrate that our synthetic-only trained model achieves state-of-the-art results in zero-shot generalization, significantly outperforming existing solutions while showing remarkable robustness to challenging cases such as mirrors and transparencies.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The 3D Mirage: Probing and Taming 3D Hallucinations

    cs.CV 2025-12 reject novelty 6.0 of 10

    Depth models hallucinate 3D bumps on flat illusion images when context is cropped; the paper adds a benchmark, two scores, and a LoRA fine-tune that reduces the artifact on the same dataset.

  2. Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Aerial depth estimation improves by using monocular depth and normals to predict adaptive depth ranges, boosting SOTA accuracy on WHU, LuoJia-MVS, and München.

  3. Diving into the Fusion of Monocular Priors for Generalized Stereo Matching

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Local ordering maps and per-pixel affine registration of monocular depth improve zero-shot generalization of iterative stereo matching on ill-posed regions.

  4. BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A single network that iteratively aligns monocular features with stereo hypotheses reduces zero-shot stereo depth error by over 40% on Middlebury and ETH3D.

Pith tools