GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations

• URL: http://arxiv.org/abs/2609.06628v2
• Date: Sat, 12 Sep 2026 12:33:44 GMT
• Title: GeoCo-SAVi: Geometry-Consistent Slot Attention for Explicitly Editable Object Representations
• Abstract summary: GeoCo-SAVi promotes geometric authority and semantic alignment.<n>On 250 MOVi-C videos, it also improves reconstruction, instance grouping, and fixed-identity geometry control.
• Score: 31.094346113912895
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object-centric video models represent scenes with slots, yet exposed geometry can vary in meaning with appearance. In Invariant Slot Attention (ISA), explicit position and scale can disagree with the decoded center and extent; edits can yield unexpected motion or resizing, and replacing appearance can shift geometry. GeoCo-SAVi promotes geometric authority and semantic alignment. Its spatially equivariant, object-wise decoder makes position and scale effective commands: changing them moves or resizes the rendered support. Factual position alignment ties position to the decoded center, and normalized attention overlap discourages duplicate allocation. Appearance transplantation aligns geometry semantics across objects, so recipient geometry governs layout while donor appearance supplies shape. A temporal initializer propagates calibrated slots across frames. On Obj3D, GeoCo-SAVi matches ISA reconstruction, reduces p-centroid error by over 80%, and cuts appearance-induced size variation by over 50% while producing the expected translation and scale responses. On 250 MOVi-C videos, it also improves reconstruction, instance grouping, and fixed-identity geometry control over two same-protocol references. GeoCo-SAVi transforms explicit geometry into compositional control, making both position and scale more readable and editable.

Related papers

• G$^2$TAM: Geometry Grounded Track Anything Model [49.05553245076823]
  We propose a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos.<n>G$2$TAM employs spatially aligned geometric representations as implicit memory, ensuring stable instance identity and localization across frames and views.<n>At its core is a cross-modal spatial encoder that integrates visual and textual prompts into a shared geometric space, enabling end-to-end spatial reconstruction and instance-consistent mask prediction.
  arXiv  Detail & Related papers  (2026-07-04T09:32:13Z)
• Geometry-Instructed Video Editing [54.86319853573801]
  GIVE is a geometry-instructed video editing framework that represents edits through a unified object-state formulation.<n>We build a scalable graphics-engine pipeline that executes object-level edit programs and renders controlled before/after pairs.<n> Experimental results demonstrate that GIVE produces faithful geometric edits with temporal coherence and consistent secondary effects.
  arXiv  Detail & Related papers  (2026-06-23T07:11:45Z)
• IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation [76.36174247570716]
  We propose IVGT, an Implicit Visual Geometry Transformer that implicitly models continuous and coherent geometry from pose-free multi-view images.<n> IVGT learns a continuous neural scene representation in a canonical coordinate system and supports continuous spatial queries at any 3D positions.<n>It allows direct extraction of continuous and coherent surface geometry, enabling rendering of RGB images, depth maps, and surface normal maps from arbitrary viewpoints.
  arXiv  Detail & Related papers  (2026-05-15T17:59:57Z)
• TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking [38.40189748889072]
  Mesh-guided 3DGS editing framework achieves automated, high-fidelity scene transformation.<n>By anchoring video diffusion with explicit 3D geometry, TRACE enables fine-grained, part-level manipulatio.
  arXiv  Detail & Related papers  (2026-04-01T17:51:00Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Dragging with Geometry: From Pixels to Geometry-Guided Image Editing [42.176957681367185]
  We propose a novel geometry-guided drag-based image editing method - GeoDrag.<n>Built upon a unified displacement field that jointly encodes 3D geometry and 2D spatial priors, GeoDrag enables coherent, high-fidelity, and structure-consistent editing.
  arXiv  Detail & Related papers  (2025-09-30T03:53:11Z)
• Leveraging Geometric Priors for Unaligned Scene Change Detection [53.523333385654546]
  Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment.<n>We introduce geometric priors for the first time to address the core challenges of unaligned SCD.<n>We propose a training-free framework that integrates them with the powerful representations of a visual foundation model.
  arXiv  Detail & Related papers  (2025-09-14T14:31:08Z)
• Geometry-Editable and Appearance-Preserving Object Compositon [67.98806888489385]
  General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties.<n>Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation.<n>We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion model that first leverages semantic embeddings to implicitly capture desired geometric transformations.
  arXiv  Detail & Related papers  (2025-05-27T09:05:28Z)
• ESCAPE: Equivariant Shape Completion via Anchor Point Encoding [79.59829525431238]
  We introduce ESCAPE, a framework designed to achieve rotation-equivariant shape completion.<n>ESCAPE employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points.<n>ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations.
  arXiv  Detail & Related papers  (2024-12-01T20:05:14Z)
• GeoDeformer: Geometric Deformable Transformer for Action Recognition [22.536307401874105]
  Vision transformers have recently emerged as an effective alternative to convolutional networks for action recognition. This paper proposes a novel approach, GeoDeformer, designed to capture the variations inherent in action video by integrating geometric comprehension directly into the ViT architecture.
  arXiv  Detail & Related papers  (2023-11-29T16:55:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.