Pith. sign in

REVIEW 10 cited by

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos

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 2412.04463 v2 pith:WW45Z2IA submitted 2024-12-05 cs.CV

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos

classification cs.CV
keywords videoscameradynamicaccuratemotionrobustscenessystem
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion and monocular SLAM techniques assume input videos that feature predominantly static scenes with large amounts of parallax. Such methods tend to produce erroneous estimates in the absence of these conditions. Recent neural network-based approaches attempt to overcome these challenges; however, such methods are either computationally expensive or brittle when run on dynamic videos with uncontrolled camera motion or unknown field of view. We demonstrate the surprising effectiveness of a deep visual SLAM framework: with careful modifications to its training and inference schemes, this system can scale to real-world videos of complex dynamic scenes with unconstrained camera paths, including videos with little camera parallax. Extensive experiments on both synthetic and real videos demonstrate that our system is significantly more accurate and robust at camera pose and depth estimation when compared with prior and concurrent work, with faster or comparable running times. See interactive results on our project page: https://mega-sam.github.io/

discussion (0)

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

Forward citations

Cited by 10 Pith papers

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

  1. Large Video Planner Enables Generalizable Robot Control

    cs.RO 2025-12 conditional novelty 7.0

    A video foundation model trained on human demonstrations generates zero-shot plans that convert to executable robot actions on novel scenes and tasks.

  2. Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos

    cs.CV 2025-04 unverdicted novelty 7.0

    A generative model produces realistic and coherent 360 panoramic videos from in-the-wild perspective videos via curated online data and geometry-motion aware operations.

  3. LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relighting

    cs.CV 2026-07 conditional novelty 6.0

    A video relighting system that refines a physically based re-render of the input under target lighting with a fine-tuned video diffusion model and reports state-of-the-art results on synthetic and real benchmarks.

  4. LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relighting

    cs.CV 2026-07 conditional novelty 6.0

    Video relighting as diffusion refinement of a target-lit PBR proxy, trained on artifact-matched synthetic pairs and real unpaired videos, beats prior SOTA on real and synthetic benchmarks.

  5. Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting

    cs.CV 2026-06 unverdicted novelty 6.0

    Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.

  6. Quantitative Video World Model Evaluation for Geometric-Consistency

    cs.CV 2026-05 unverdicted novelty 6.0

    PDI-Bench computes 3D projective residuals from segmented and tracked points to quantify geometric inconsistency in AI-generated videos.

  7. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0

    Spatial-MLLM adds a 3D spatial encoder initialized from a visual geometry model and space-aware frame sampling to MLLMs to improve spatial understanding and reasoning from purely 2D visual inputs.

  8. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

    cs.CV 2025-05 unverdicted novelty 6.0

    Spatial-MLLM boosts MLLM spatial intelligence from 2D inputs via dual encoders initialized from geometry models plus space-aware sampling, claiming state-of-the-art results.

  9. NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction

    cs.CV 2026-07 conditional novelty 5.0

    Injecting frozen monocular depth features into neural structured-light decoding cuts Replica-SL depth RMSE ~35% vs NSL and, with depth-centric GICP+sparse anchors+light BA, yields the most stable real D435 SLAM among ...

  10. 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.