A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
Blenderproc2: A procedural pipeline for photorealistic rendering
5 Pith papers cite this work. Polarity classification is still indexing.
years
2026 5representative citing papers
A review paper that organizes industrial visual sim-to-real literature into CAD-available, CAD-unavailable, and boundary-prior regimes based on the type of prior information available.
SynthRender and IRIS enable synthetic-data training that reaches 95-99% mAP@50 on real industrial object detection benchmarks across robotics and automotive settings.
CLASP combines TP-KMPs with VLMs for language-guided skill selection, covariance-weighted composition, and active learning requests, reporting 73.3-100% success on a 7-DoF manipulator.
A new synthetic dataset and geometry-consistent dense correspondence framework improve RGB-only pose estimation accuracy for surgical instruments on three evaluation datasets.
citing papers explorer
-
A Causal Diffusion Model for Video Reconstruction from Ultra-Low-Bitrate Representations
A causal diffusion model reconstructs videos from ultra-low-bitrate semantics and compressed frames using temporal distillation from a bidirectional teacher, outperforming prior baselines.
-
Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes
A review paper that organizes industrial visual sim-to-real literature into CAD-available, CAD-unavailable, and boundary-prior regimes based on the type of prior information available.
-
CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Learning
CLASP combines TP-KMPs with VLMs for language-guided skill selection, covariance-weighted composition, and active learning requests, reporting 73.3-100% success on a 7-DoF manipulator.
-
SurfSurg6D: Geometry Consistent Dense Correspondence for Textureless Surgical Instrument Pose Estimation
A new synthetic dataset and geometry-consistent dense correspondence framework improve RGB-only pose estimation accuracy for surgical instruments on three evaluation datasets.