5 papers
Toward A Better Understanding of Monocular Depth Evaluation
Siyang Wu, Jack Nugent, Willow Yang +1
Monocular depth estimation is an important task with rapid progress, but how to evaluate it is not fully resolved, as evidenced by a lack of standardization in existing literature…
Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
Jack Nugent, Siyang Wu, Zeyu Ma +7
Recent years have witnessed substantial progress on monocular depth estimation, particularly as measured by the success of large models on standard benchmarks. However, performance…
Procedural Generation of Articulated Simulation-Ready Assets
Abhishek Joshi, Beining Han, Jack Nugent +12
We introduce Infinigen-Articulated, a toolkit for generating realistic, procedurally generated articulated assets for robotics simulation. We include procedural generators for 18 c…
What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
David Yan, Alexander Raistrick, Jia Deng
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 t…
LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow
Hongyu Wen, Erich Liang, Jia Deng
Achieving 3D understanding of non-Lambertian objects is an important task with many useful applications, but most existing algorithms struggle to deal with such objects. One major…