REVIEW 7 cited by
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
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
Indoor robotics localization, navigation, and interaction heavily rely on scene understanding and reconstruction. Compared to the monocular vision which usually does not explicitly introduce any geometrical constraint, stereo vision-based schemes are more promising and robust to produce accurate geometrical information, such as surface normal and depth/disparity. Besides, deep learning models trained with large-scale datasets have shown their superior performance in many stereo vision tasks. However, existing stereo datasets rarely contain the high-quality surface normal and disparity ground truth, which hardly satisfies the demand of training a prospective deep model for indoor scenes. To this end, we introduce a large-scale synthetic but naturalistic indoor robotics stereo (IRS) dataset with over 100K stereo RGB images and high-quality surface normal and disparity maps. Leveraging the advanced rendering techniques of our customized rendering engine, the dataset is considerably close to the real-world captured images and covers several visual effects, such as brightness changes, light reflection/transmission, lens flare, vivid shadow, etc. We compare the data distribution of IRS with existing stereo datasets to illustrate the typical visual attributes of indoor scenes. Besides, we present DTN-Net, a two-stage deep model for surface normal estimation. Extensive experiments show the advantages and effectiveness of IRS in training deep models for disparity estimation, and DTN-Net provides state-of-the-art results for normal estimation compared to existing methods.
Forward citations
Cited by 7 Pith papers
-
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
A dual-branch transformer with masked joint attention completes dense metric depth from sparse dToF sensors, trained entirely on synthetic data and generalizing zero-shot to real devices.
-
MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
Iterative sparse-3D-convolution refinement in a log-depth voxel shell, instead of 2D image-plane refinement, sharply improves fine-detail geometry in monocular point maps and sets state of the art on local fine-detail...
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal
A unified stereo framework couples feed-forward disparity matching with a diffusion-based normal estimator through disparity-to-normal initialization and warped right-view conditioning, claiming zero-shot SOTA on seve...
-
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
A sparse-prompt pretraining framework on 20M heterogeneous image-depth pairs yields a scaling trend and state-of-the-art metric depth across many downstream tasks.
-
2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
Entropy-guided sparse refinement upgrades frozen low-resolution geometric foundation models to accurate 2K depth and pointmap outputs at a fraction of full-resolution cost.
-
AutoML: A Survey of the State-of-the-Art
A survey that organizes AutoML into a four-stage pipeline and reviews neural architecture search methods, their performance, and open problems.
Discussion (0). Continue with ORCID to comment.