What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?

• URL: http://arxiv.org/abs/2504.16930v2
• Date: Mon, 03 Nov 2025 18:59:31 GMT
• Title: What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
• Authors: David Yan, Alexander Raistrick, Jia Deng,
• Abstract summary: We report the effects on zero-shot stereo matching performance using standard benchmarks.<n>We validate our findings by collecting the best settings and creating a large-scale dataset.<n>We open-source our system to enable further research on procedural stereo datasets.
• Score: 57.49867420132091
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator, and report the effects on zero-shot stereo matching performance using standard benchmarks. We validate our findings by collecting the best settings and creating a large-scale dataset. Training only on this dataset achieves better performance than training on a mixture of widely used datasets, and is competitive with training on the FoundationStereo dataset, with the additional benefit of open-source generation code and an accompanying parameter analysis to enable further research. We open-source our system at https://github.com/princeton-vl/InfinigenStereo to enable further research on procedural stereo datasets.

Related papers

• Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling [31.51048512214796]
  dataset distillation aims to generate compact, high-quality synthetic datasets that can achieve comparable performance to the original dataset.<n>We propose a task-specific sampling strategy for generative dataset distillation that incorporates the concept of difficulty to consider the requirements of the target task better.<n>The results of extensive experiments demonstrate the effectiveness of our method and suggest its potential for enhancing performance on other downstream tasks.
  arXiv  Detail & Related papers  (2025-07-04T06:38:02Z)
• Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer [16.040335263873278]
  We introduce a 3D Gaussian Splatting (3DGS)-based pipeline for stereo dataset generation, offering an efficient alternative to Neural Radiance Fields (NeRF)-based methods.<n>We find that when fine-tuning stereo models on 3DGS-generated datasets, we demonstrate competitive performance in zero-shot generalization benchmarks.
  arXiv  Detail & Related papers  (2025-06-05T11:41:09Z)
• FoundationStereo: Zero-Shot Stereo Matching [50.79202911274819]
  FoundationStereo is a foundation model for stereo depth estimation. We first construct a large-scale (1M stereo pairs) synthetic training dataset. We then design a number of network architecture components to enhance scalability.
  arXiv  Detail & Related papers  (2025-01-17T01:01:44Z)
• Generating Realistic Tabular Data with Large Language Models [49.03536886067729]
  Large language models (LLM) have been used for diverse tasks, but do not capture the correct correlation between the features and the target variable. We propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. Our experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks.
  arXiv  Detail & Related papers  (2024-10-29T04:14:32Z)
• Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data [69.7174072745851]
  We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data.<n>To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization.<n>To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models.
  arXiv  Detail & Related papers  (2024-10-02T22:05:36Z)
• Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment [39.137060714048175]
  We argue that enhancing diversity can improve the parallelizable yet isolated approach to synthesizing datasets. We introduce a novel method that employs dynamic and directed weight adjustment techniques to modulate the synthesis process. Our method ensures that each batch of synthetic data mirrors the characteristics of a large, varying subset of the original dataset.
  arXiv  Detail & Related papers  (2024-09-26T08:03:19Z)
• Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark [65.79402756995084]
  Real Acoustic Fields (RAF) is a new dataset that captures real acoustic room data from multiple modalities. RAF is the first dataset to provide densely captured room acoustic data.
  arXiv  Detail & Related papers  (2024-03-27T17:59:56Z)
• TarGEN: Targeted Data Generation with Large Language Models [51.87504111286201]
  TarGEN is a multi-step prompting strategy for generating high-quality synthetic datasets. We augment TarGEN with a method known as self-correction empowering LLMs to rectify inaccurately labeled instances. A comprehensive analysis of the synthetic dataset compared to the original dataset reveals similar or higher levels of dataset complexity and diversity.
  arXiv  Detail & Related papers  (2023-10-27T03:32:17Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• Dataset Distillation by Matching Training Trajectories [75.9031209877651]
  We propose a new formulation that optimize our distilled data to guide networks to a similar state as those trained on real data. Given a network, we train it for several iterations on our distilled data and optimize the distilled data with respect to the distance between the synthetically trained parameters and the parameters trained on real data. Our method handily outperforms existing methods and also allows us to distill higher-resolution visual data.
  arXiv  Detail & Related papers  (2022-03-22T17:58:59Z)
• On the use of automatically generated synthetic image datasets for benchmarking face recognition [2.0196229393131726]
  Recent advances in Generative Adversarial Networks (GANs) provide a pathway to replace real datasets by synthetic datasets. Recent advances in Generative Adversarial Networks (GANs) to synthesize realistic face images provide a pathway to replace real datasets by synthetic datasets. benchmarking results on the synthetic dataset are a good substitution, often providing error rates and system ranking similar to the benchmarking on the real dataset.
  arXiv  Detail & Related papers  (2021-06-08T09:54:02Z)
• PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching [14.603116313499648]
  We propose a robust and effective self-supervised stereo matching approach, consisting of a pyramid voting module (PVM) and a novel DCNN architecture, referred to as OptStereo. Specifically, our OptStereo first builds multi-scale cost volumes, and then adopts a recurrent unit to iteratively update disparity estimations at high resolution. We publish the HKUST-Drive dataset, a large-scale synthetic stereo dataset, collected under different illumination and weather conditions for research purposes.
  arXiv  Detail & Related papers  (2021-03-12T05:27:14Z)
• Semi-synthesis: A fast way to produce effective datasets for stereo matching [16.602343511350252]
  Close-to-real-scene texture rendering is a key factor to boost up stereo matching performance. We propose semi-synthetic, an effective and fast way to synthesize large amount of data with close-to-real-scene texture. With further fine-tuning on the real dataset, we also achieve SOTA performance on Middlebury and competitive results on KITTI and ETH3D datasets.
  arXiv  Detail & Related papers  (2021-01-26T14:34:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.