SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction

• URL: http://arxiv.org/abs/2512.02609v1
• Date: Tue, 02 Dec 2025 10:15:00 GMT
• Title: SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction
• Authors: Shengkai Wu, Jinrong Yang, Wenqiu Luo, Linfeng Gao, Chaohui Shang, Meiyu Zhi, Mingshan Sun, Fangping Yang, Liangliang Ren, Yong Zhao,
• Abstract summary: Imitation learning for robotic grasping is often plagued by the multimodal problem.<n>Standard imitation learning policies fail by averaging these distinct actions into a single, invalid action.<n>We introduce SAM2Grasp, a novel framework that reformulating the task as a uni-modal, prompt-conditioned prediction problem.
• Score: 7.708279811172532
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Imitation learning for robotic grasping is often plagued by the multimodal problem: when a scene contains multiple valid targets, demonstrations of grasping different objects create conflicting training signals. Standard imitation learning policies fail by averaging these distinct actions into a single, invalid action. In this paper, we introduce SAM2Grasp, a novel framework that resolves this issue by reformulating the task as a uni-modal, prompt-conditioned prediction problem. Our method leverages the frozen SAM2 model to use its powerful visual temporal tracking capability and introduces a lightweight, trainable action head that operates in parallel with its native segmentation head. This design allows for training only the small action head on pre-computed temporal-visual features from SAM2. During inference, an initial prompt, such as a bounding box provided by an upstream object detection model, designates the specific object to be grasped. This prompt conditions the action head to predict a unique, unambiguous grasp trajectory for that object alone. In all subsequent video frames, SAM2's built-in temporal tracking capability automatically maintains stable tracking of the selected object, enabling our model to continuously predict the grasp trajectory from the video stream without further external guidance. This temporal-prompted approach effectively eliminates ambiguity from the visuomotor policy. We demonstrate through extensive experiments that SAM2Grasp achieves state-of-the-art performance in cluttered, multi-object grasping tasks.

Related papers

• SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking [58.35852822355312]
  Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos.<n>To address these issues, some methods propose to adapt the video foundation model SAM2 for VOT, where the tracking results of each frame would be encoded as memory for conditioning the rest of frames in an autoregressive manner.<n>We present a SAMITE model, built upon SAM2 with additional modules, to tackle these challenges.
  arXiv  Detail & Related papers  (2025-07-29T12:11:56Z)
• SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation [4.166500345728911]
  Referring Video Object (RVOS) relies on natural language expressions to segment an object in a video clip.<n>We build upon the Segment-Anything 2 (SAM2) model, that provides robust segmentation and tracking capabilities.<n>We introduce a novel adapter module that injects temporal information and multi-modal cues in the feature extraction process.
  arXiv  Detail & Related papers  (2024-11-26T18:10:54Z)
• SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention [0.0]
  The Segment Anything Model (SAM) has gained notable recognition for its exceptional performance in image segmentation. Camouflaged objects typically blend into the background, making them difficult to distinguish in still images. We propose a new method called the SAM Spider Module (SAM-PM) to overcome these challenges. Our method effectively incorporates temporal consistency and domain-specific expertise into the segmentation network with an addition of less than 1% of SAM's parameters.
  arXiv  Detail & Related papers  (2024-06-09T14:33:38Z)
• DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
  Our approach formulates the union of the two tasks as a trajectory refinement problem. To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects. In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
  arXiv  Detail & Related papers  (2024-06-06T18:12:04Z)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.<n>Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction.<n>We benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising [37.216493829454706]
  We explore the potential of applying the Segment Anything Model to track and segment objects in videos. Specifically, we iteratively propagate the bounding box of each object's mask in the preceding frame as the prompt for the next frame. To enhance SAM's denoising capability against position and size variations, we propose a multi-prompt strategy.
  arXiv  Detail & Related papers  (2024-03-07T03:52:59Z)
• SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features [52.213656737672935]
  SpikeMOT is an event-based multi-object tracker. SpikeMOT uses spiking neural networks to extract sparsetemporal features from event streams associated with objects.
  arXiv  Detail & Related papers  (2023-09-29T05:13:43Z)
• DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks [77.84636815364905]
  This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks.<n>We propose DropMAE, which adaptively performs spatial-attention dropout in the frame reconstruction to facilitate temporal correspondence learning in videos.
  arXiv  Detail & Related papers  (2023-04-02T16:40:42Z)
• MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection [76.80153360498797]
  We develop a multiple instance self-training framework (MIST) to efficiently refine task-specific discriminative representations. MIST is composed of 1) a multiple instance pseudo label generator, which adapts a sparse continuous sampling strategy to produce more reliable clip-level pseudo labels, and 2) a self-guided attention boosted feature encoder. Our method performs comparably to or even better than existing supervised and weakly supervised methods, specifically obtaining a frame-level AUC 94.83% on ShanghaiTech.
  arXiv  Detail & Related papers  (2021-04-04T15:47:14Z)
• Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning [54.90704746573636]
  Our method does not require to manually select key frames, and produces state-of-the-art results with as little as $2%$ of annotated frames. We experimentally validate that our method outperforms existing methods when working with as little as $2%$ of randomly chosen data.
  arXiv  Detail & Related papers  (2020-11-03T17:35:57Z)

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.