Pith. sign in

REVIEW 12 cited by

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

arxiv 1912.09678 v2 pith:SPERYRUV submitted 2019-12-20 cs.CV cs.RO

IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation

classification cs.CV cs.RO
keywords stereonormaldeepdisparityindoorsurfaceestimationdataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. Vision as Unified Multimodal Generation

    cs.CV 2026-07 conditional novelty 7.0

    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.

  2. DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

    cs.CV 2026-06 unverdicted novelty 7.0

    DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspectiv...

  3. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

    cs.CV 2023-02 accept novelty 7.0

    ZoeDepth combines relative depth pre-training on many datasets with metric depth fine-tuning and automatic head routing to achieve strong zero-shot generalization while preserving metric scale.

  4. GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

    cs.CV 2026-05 unverdicted novelty 6.0

    GemDepth adds explicit camera-pose geometry embeddings and an alternating spatio-temporal transformer to produce sharper, more temporally consistent video depth maps than prior smoothing-based methods.

  5. GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

    cs.CV 2026-05 unverdicted novelty 6.0

    GemDepth achieves improved 3D-consistent video depth by embedding predicted inter-frame camera poses into a network with an Alternating Spatio-Temporal Transformer for better spatial precision and temporal coherence.

  6. GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

    cs.CV 2026-05 unverdicted novelty 6.0

    GemDepth embeds predicted camera poses into a spatio-temporal transformer to achieve state-of-the-art 3D-consistent video depth estimation.

  7. GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth

    cs.CV 2026-05 unverdicted novelty 6.0

    GemDepth predicts inter-frame camera poses to inject geometric embeddings into a spatio-temporal transformer, yielding state-of-the-art 3D-consistent video depth.

  8. Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

    cs.CV 2025-11 unverdicted novelty 6.0

    Lotus-2 is a two-stage deterministic adaptation of diffusion priors that achieves state-of-the-art monocular depth estimation with only 59K training samples.

  9. Lite Any Stereo: Efficient Zero-Shot Stereo Matching

    cs.CV 2025-11 unverdicted novelty 6.0

    Lite Any Stereo delivers top-ranked zero-shot accuracy on four real-world stereo benchmarks using a lightweight backbone, hybrid cost aggregation, and three-stage training on million-scale data, at less than 1% of typ...

  10. Depth Anything 3: Recovering the Visual Space from Any Views

    cs.CV 2025-11 unverdicted novelty 6.0

    DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.

  11. Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching

    cs.CV 2026-06 unverdicted novelty 5.0

    LAS2 is a series of efficient stereo matching models that reach state-of-the-art zero-shot performance among fast methods while running 1.8-2.7x faster than prior iterative approaches on H200 and Orin hardware.

  12. MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

    cs.CV 2025-07 unverdicted novelty 5.0

    MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.