mlsanityData to 7 Oct 2026

Affostruction: 3D Affordance Grounding with Generative Reconstruction

arXiv 2601.09211 ↗First posted 14 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of affordance grounding from RGBD images of an object, which aims to localize surface regions corresponding to a text query that describes an action on the object. While existing methods predict affordance regions only on visible surfaces, we propose Affostruction, a generative framework that reconstructs complete object geometry from partial RGBD observations and grounds affordances on the full shape including unobserved regions. Our approach introduces sparse voxel fusion of multi-view features for constant-complexity generative reconstruction, a flow-based formulation that captures the inherent ambiguity of affordance distributions, and an active view selection strategy guided by predicted affordances. Affostruction outperforms existing methods by large margins on challenging benchmarks, achieving 19.1 aIoU on affordance grounding and 32.67 IoU for 3D reconstruction.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

48 of 56 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 2025Gemma 3 Technical Reportcited by 1,686
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
36 more
  1. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  2. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  3. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  4. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  5. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  6. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  7. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  8. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  9. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  10. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  11. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  12. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  13. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  14. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  15. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  16. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  17. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  18. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  19. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  20. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  21. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 148
  22. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  23. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  24. 2021Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representationscited by 107
  25. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  26. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 100
  27. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  28. 2021AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactionscited by 56
  29. 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
  30. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
  31. 2025Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactionscited by 19
  32. 2023DreamComposer: Controllable 3D Object Generation via Multi-View Conditionscited by 18
  33. 2023Language-Conditioned Affordance-Pose Detection in 3D Point Cloudscited by 16
  34. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  35. 2023MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D Generationcited by 8
  36. 2025Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scalecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objectscited by 1