# AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning

arXiv: https://arxiv.org/abs/2608.20720 · HTML: https://mlsanity.com/paper/2608.20720/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 43 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)

## Abstract (arXiv)

Open-world 3D affordance grounding requires localizing functional object parts in 3D given free-form language queries. Existing methods typically assume pre-built object-centric 3D geometry and closed affordance ontologies, limiting deployment from raw RGB observations. We present AffordAny, an end-to-end framework that uses one monocular RGB image to construct large-scale text-conditioned 3D part supervision, ground affordances with a frozen vision-language model (VLM) guided decoder, and improve open-world generalization through pseudo-label self-training. Our automated pipeline produces a benchmark of 5,334 objects and 10,633 part-level samples spanning 473 categories, an order-of-magnitude increase in categorical diversity over prior work. The decoder progressively fuses frozen Cosmos-2B features with 3D geometry through spatial projection, instruction-conditioned semantic compression, and bidirectional geometry-semantics interaction. Minimal-perturbation pseudo-label self-training further adds new objects without human annotation. Under a systematic generalization protocol evaluating unseen objects, unseen categories, and unseen instruction paraphrases, our approach achieves 0.428 IoU on unseen objects and 0.315 IoU on unseen categories after self-training, with unseen-category mIoU improving by 6.3% relative (p<0.01) and an instruction sensitivity gap of only 0.105, demonstrating effectiveness and robustness of our method.