# Joint-Conditioned Stereo Surface Reasoning for Interaction Field Estimation

arXiv: https://arxiv.org/abs/2609.06955 · HTML: https://mlsanity.com/paper/2609.06955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 4 references that are in the map.
- First posted on arXiv 7 Sep 2026.

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

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Efficiently Reconstructing Dynamic Scenes One D4RT at a Time](https://mlsanity.com/paper/2512.08924/) (2025)
- [SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild](https://mlsanity.com/paper/2603.28760/) (2026)

## Abstract (arXiv)

Predicting hand--object interaction fields requires locating the nearest object-surface point for each hand joint, often from small and partially occluded image regions. We view this task as joint-conditioned surface-endpoint estimation: each joint has its own nearest endpoint, while endpoints from the same hand can draw on shared local surface evidence. This structure motivates Joint-Conditioned Stereo Surface Reasoning (JSSR). A temporal-stereo network jointly predicts 3D joints, a direct interaction field, and per-view endpoint evidence. Calibrated candidate search evaluates endpoint hypotheses using joint-specific image compatibility and cross-view correspondence. A hand-shared candidate support lets joints draw on common surface evidence, and a learned residual gate controls the geometric correction when observations are ambiguous. Our system built on this method ranked third on the SHOW3D Interaction Field Challenge leaderboard.