REVIEW 7 cited by
FoundationStereo: Zero-Shot Stereo Matching
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation. Project page: https://nvlabs.github.io/FoundationStereo/
Forward citations
Cited by 7 Pith papers
-
TiPToP: A Modular Open-Vocabulary Robot Manipulation System That Plans
TiPToP, a zero-training modular planner using pretrained vision-language models and GPU-accelerated TAMP, achieves 74.6% success over 165 trials versus 52.4% for the 350-hour-trained pi0.5-DROID baseline across 28 man...
-
3PoinTr: 3D Point Tracks for Learning Manipulation from Unconstrained Human Videos
Dense 3D point-track prediction from unconstrained human videos plus a track-conditioned closed-loop policy yields large sample-efficiency gains over BC and video-pretraining baselines.
-
ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation
ParticleFormer uses a Transformer over point-cloud particles and a hybrid Chamfer-Hausdorff loss to predict multi-material object dynamics, and it reports lower errors than GNN and image-based baselines in simulation ...
-
Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
Two differently blurred images plus a pretrained diffusion depth prior are optimized together at inference time to recover metric depth without retraining.
-
Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
Local ordering maps and per-pixel affine registration of monocular depth improve zero-shot generalization of iterative stereo matching on ill-posed regions.
-
Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
The abstract claims a systematic benchmark of universal machine-learned potentials on biomolecular simulations, but the body text supplied is an unrelated stereo-vision paper, leaving the claim unverifiable.
-
BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
A single network that iteratively aligns monocular features with stereo hypotheses reduces zero-shot stereo depth error by over 40% on Middlebury and ETH3D.
Discussion (0). Continue with ORCID to comment.