Pith. sign in

REVIEW 10 cited by

DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation

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 2312.00583 v2 pith:SLKOMZRR submitted 2023-11-30 cs.CV cs.RO

DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation

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

Teaching robots to fold, drape, or reposition deformable objects such as cloth will unlock a variety of automation applications. While remarkable progress has been made for rigid object manipulation, manipulating deformable objects poses unique challenges, including frequent occlusions, infinite-dimensional state spaces and complex dynamics. Just as object pose estimation and tracking have aided robots for rigid manipulation, dense 3D tracking (scene flow) of highly deformable objects will enable new applications in robotics while aiding existing approaches, such as imitation learning or creating digital twins with real2sim transfer. We propose DeformGS, an approach to recover scene flow in highly deformable scenes, using simultaneous video captures of a dynamic scene from multiple cameras. DeformGS builds on recent advances in Gaussian splatting, a method that learns the properties of a large number of Gaussians for state-of-the-art and fast novel-view synthesis. DeformGS learns a deformation function to project a set of Gaussians with canonical properties into world space. The deformation function uses a neural-voxel encoding and a multilayer perceptron (MLP) to infer Gaussian position, rotation, and a shadow scalar. We enforce physics-inspired regularization terms based on conservation of momentum and isometry, which leads to trajectories with smaller trajectory errors. We also leverage existing foundation models SAM and XMEM to produce noisy masks, and learn a per-Gaussian mask for better physics-inspired regularization. DeformGS achieves high-quality 3D tracking on highly deformable scenes with shadows and occlusions. In experiments, DeformGS improves 3D tracking by an average of 55.8% compared to the state-of-the-art. With sufficient texture, DeformGS achieves a median tracking error of 3.3 mm on a cloth of 1.5 x 1.5 m in area. Website: https://deformgs.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. ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment

    cs.CV 2026-08 conditional novelty 7.0

    ASTRA jointly estimates camera time offsets and dynamic Gaussian geometry by aligning projected 3D motion with observed 2D trajectory tracks, improving robustness to large asynchrony.

  2. Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

    cs.RO 2026-07 conditional novelty 7.0

    Deform360 supplies 215+ hours of synchronized multi-view video and tactile data plus markerless 3D tracks, revealing that 3D particle models win in low data while 2D video models generalize better at scale.

  3. DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming

    cs.CV 2026-06 unverdicted novelty 7.0

    DLGStream introduces dual-opacity dynamic language Gaussians and an interpolation deformation field to enable language-embedded FVV streaming at 43 KB per frame with improved open-vocabulary segmentation and reconstru...

  4. Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement

    cs.CV 2026-04 unverdicted novelty 7.0

    The paper presents a multimodal framework, dataset, and reconstruction pipeline to create immersive volumetric videos supporting large 6-DoF audiovisual interaction from real multi-view captures.

  5. GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 7.0

    GEAR is an EM-style alternating optimization framework that jointly models geometry and motion in Gaussian Splatting to improve reconstruction of complex articulated objects.

  6. PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming

    cs.CV 2026-05 unverdicted novelty 6.0

    PD-4DGS decomposes 4DGS into static scaffold, global deformation, and local refinement layers using hierarchical decomposition and custom losses, achieving over 60% bitstream reduction and reducing first-frame latency...

  7. WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations

    cs.RO 2026-04 unverdicted novelty 6.0

    WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match tele...

  8. LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting

    cs.HC 2024-12 unverdicted novelty 5.0

    LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.

  9. From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 4.0

    A framework is introduced to systematically assess the reconstruction fidelity of 3D Gaussian Splatting for vehicles and pedestrians in autonomous driving scenes from novel lateral and longitudinal viewpoints.

  10. Advances in 4D Representation: Geometry, Motion, and Interaction

    cs.CV 2025-10 conditional novelty 4.0

    A representation-centric survey of 4D generation and reconstruction, organized by geometry, motion, and interaction, with qualitative trade-off comparisons across seven representation families.