EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
hub
arXiv preprint arXiv:2304.06790 (2023)
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
other 1
citation-polarity summary
representative citing papers
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
Delta-Adapter extracts a semantic delta from a single image pair via a pre-trained vision encoder and injects it through a Perceiver adapter to enable scalable single-pair supervised editing.
DiffusionPrint learns robust forensic feature maps via MoCo-style contrastive training on diffusion inpainting fingerprints, boosting localization accuracy by up to 28% when fused into existing IFL systems and generalizing to unseen models.
COCO-Inpaint supplies a large-scale dataset and evaluation protocol focused on inpainting-based image forgeries to benchmark existing detection methods.
TeleMorpher introduces a training-free pose-warping pipeline plus two LPIPS-based metrics for simultaneous motion and location editing in videos, claiming superior results on in-the-wild and TaiChi data.
SAM-Flow introduces source-anchored masked flows with dynamic soft masks for localized training-free semantic editing in diffusion and flow models.
ClickRemoval delivers click-driven object removal and background restoration in diffusion models through self-attention modulation without additional training or inputs.
WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match teleoperation success rates on five tabletop tasks with 5-8x less collection effort.
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
GASE automates high-fidelity simulation scene reconstruction from multi-view panoramic videos via Gaussian splatting, object extraction, and inpainting, yielding robot policies with under 10% performance gap versus real-world training.
An automated annotation pipeline combining Grounded DINO and SAM produces usable bounding boxes and masks for weakly supervised defect detection in shearography.
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
SPHINX improves multi-modal LLMs through joint mixing of weights, tasks, and visual embeddings from varied sources to achieve stronger alignment and multi-purpose capabilities.
MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.
citing papers explorer
-
EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations
EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
-
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
-
Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
Delta-Adapter extracts a semantic delta from a single image pair via a pre-trained vision encoder and injects it through a Perceiver adapter to enable scalable single-pair supervised editing.
-
DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization
DiffusionPrint learns robust forensic feature maps via MoCo-style contrastive training on diffusion inpainting fingerprints, boosting localization accuracy by up to 28% when fused into existing IFL systems and generalizing to unseen models.
-
COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations
COCO-Inpaint supplies a large-scale dataset and evaluation protocol focused on inpainting-based image forgeries to benchmark existing detection methods.
-
TeleMorpher: Toward Robust Simultaneous Motion-Location Editing
TeleMorpher introduces a training-free pose-warping pipeline plus two LPIPS-based metrics for simultaneous motion and location editing in videos, claiming superior results on in-the-wild and TaiChi data.
-
SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing
SAM-Flow introduces source-anchored masked flows with dynamic soft masks for localized training-free semantic editing in diffusion and flow models.
-
ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models
ClickRemoval delivers click-driven object removal and background restoration in diffusion models through self-attention modulation without additional training or inputs.
-
WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations
WARPED synthesizes realistic wrist-view observations from monocular egocentric human videos via foundation models, hand-object tracking, retargeting, and Gaussian Splatting to train visuomotor policies that match teleoperation success rates on five tabletop tasks with 5-8x less collection effort.
-
IGen: Scalable Data Generation for Robot Learning from Open-World Images
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
-
GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
GASE automates high-fidelity simulation scene reconstruction from multi-view panoramic videos via Gaussian splatting, object extraction, and inpainting, yielding robot policies with under 10% performance gap versus real-world training.
-
Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection
An automated annotation pipeline combining Grounded DINO and SAM produces usable bounding boxes and masks for weakly supervised defect detection in shearography.
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
-
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
SPHINX improves multi-modal LLMs through joint mixing of weights, tasks, and visual embeddings from varied sources to achieve stronger alignment and multi-purpose capabilities.
-
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.
- Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications
- On Efficient Variants of Segment Anything Model: A Survey