SHOW is a mask-promptable framework coupling feed-forward scene reconstruction with human mesh recovery in a unified metric space to resolve scale ambiguity and improve human-scene alignment from monocular video.
hub
Sam 3d body: Robust full-body human mesh recovery
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
hub tools
citation-role summary
method 2
background 1
citation-polarity summary
years
2026 25representative citing papers
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
H-Flow learns dense human scene flow from monocular video via joint pose and depth prediction in a multi-head transformer, using physics-inspired geometric and biomechanical priors for self-supervision, and introduces the DynAct4D synthetic benchmark.
LEXIS-Flow uses VQ-VAE-learned interaction signatures to guide diffusion-based reconstruction of 3D human-object meshes and dense proximity fields from single RGB images, outperforming SOTA on benchmarks.
DanceCrafter generates high-fidelity, text-controlled dance sequences using a new Choreographic Syntax framework and a large fine-grained motion dataset.
Vision-language models perform only marginally above random on action quality assessment and retain systematic biases even after targeted prompting and contrastive reformulation.
CoMind releases 41 h of synchronized multi-view cooking collaboration with social-cue annotations and three ToM-oriented benchmarks on which current VLMs score poorly until fine-tuned.
WNM decouples video generation into agent-built editable 4D physical narratives that condition frozen foundation models, reducing gacha-style resampling and improving layout, motion, and camera control.
Introduces a 9136-sample multi-view in-cabin dataset from a German city bus with RGB, depth, LiDAR, 3D annotations via pseudo-labeling, nuScenes conversion, and benchmarks on models like BEVFusion.
ActiveMimic pretrains on egocentric human video by recovering and modeling active camera motion as viewpoint actions, matching robot-data pretraining performance on real-world tasks.
PRIMA boosts 3D quadruped mesh recovery by injecting BioCLIP biological priors and using test-time adaptation with 2D constraints to build the Quadruped3D pseudo-3D dataset and reach SOTA on imbalanced animal benchmarks.
MAEM is a training-free framework that combines monocular 3D mesh recovery with a two-stage epipolar matching strategy using disjoint-set-union clustering and per-joint triangulation for multi-view multi-person 3D pose estimation in basketball.
SUGAR turns diverse human videos into deployable humanoid loco-manipulation policies via automated prior extraction, physics refinement, and hierarchical distillation, showing scaling with data volume and zero-shot real-world transfer on six tasks.
Method converts exocentric videos to egocentric format via body-pose extraction and kinematics to improve egocentric world-model prediction and planning.
HA-HOI produces physically plausible 4D HOI animations from monocular videos by anchoring object reconstruction to human motion and refining the result in a physics-based humanoid-object simulator.
SAMe grounds complaints to organs, builds a lightweight patient anatomy model from one body image, and outputs probe initialization poses, outperforming keypoint baselines in real-robot liver and kidney trials.
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
Pi-HOC predicts dense 3D semantic contacts for all human-object pairs in an image via instance-aware tokens and an InteractionFormer, achieving higher accuracy and 20x throughput than prior methods.
RoSHI is a hybrid wearable that combines sparse IMUs and egocentric SLAM to capture accurate full-body 3D pose and shape data in natural environments for robot learning.
DUET pretrains collaborative policies on human-human VR demonstrations then fine-tunes on minimal robot teleoperation data, achieving equal or better performance than robot-only baselines with 5.4x faster collection across four tasks.
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
Asset Harvester converts sparse in-the-wild object observations from AV driving logs into complete simulation-ready 3D assets via data curation, geometry-aware preprocessing, and a SparseViewDiT model that couples sparse-view multiview generation with 3D Gaussian lifting.
A minimal Gaussian splatting avatar pipeline using the Momentum Human Rig achieves the highest reported PSNR on PeopleSnapshot and ZJU-MoCap without learned deformations.
LUNA is an LBS-free neural animation model that maps 2D controls to 3D Gaussian deformations via a transformer motion regressor and hybrid supervision for realistic motion and zero-shot generalization.
citing papers explorer
-
Scene and Human in One World: Reconstruction in a Feedforward Pass
SHOW is a mask-promptable framework coupling feed-forward scene reconstruction with human mesh recovery in a unified metric space to resolve scale ambiguity and improve human-scene alignment from monocular video.
-
From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
-
H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
H-Flow learns dense human scene flow from monocular video via joint pose and depth prediction in a multi-head transformer, using physics-inspired geometric and biomechanical priors for self-supervision, and introduces the DynAct4D synthetic benchmark.
-
LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image
LEXIS-Flow uses VQ-VAE-learned interaction signatures to guide diffusion-based reconstruction of 3D human-object meshes and dense proximity fields from single RGB images, outperforming SOTA on benchmarks.
-
DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax
DanceCrafter generates high-fidelity, text-controlled dance sequences using a new Choreographic Syntax framework and a large fine-grained motion dataset.
-
Can Vision Language Models Judge Action Quality? An Empirical Evaluation
Vision-language models perform only marginally above random on action quality assessment and retain systematic biases even after targeted prompting and contrastive reformulation.
-
CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views
CoMind releases 41 h of synchronized multi-view cooking collaboration with social-cue annotations and three ToM-oriented benchmarks on which current VLMs score poorly until fine-tuned.
-
World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration
WNM decouples video generation into agent-built editable 4D physical narratives that condition frozen foundation models, reducing gacha-style resampling and improving layout, motion, and camera control.
-
Multi-View In-Cabin Monitoring System for Public Transport Vehicles
Introduces a 9136-sample multi-view in-cabin dataset from a German city bus with RGB, depth, LiDAR, 3D annotations via pseudo-labeling, nuScenes conversion, and benchmarks on models like BEVFusion.
-
ActiveMimic: Egocentric Video Pretraining with Active Perception
ActiveMimic pretrains on egocentric human video by recovering and modeling active camera motion as viewpoint actions, matching robot-data pretraining performance on real-world tasks.
-
PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation
PRIMA boosts 3D quadruped mesh recovery by injecting BioCLIP biological priors and using test-time adaptation with 2D constraints to build the Quadruped3D pseudo-3D dataset and reach SOTA on imbalanced animal benchmarks.
-
Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball
MAEM is a training-free framework that combines monocular 3D mesh recovery with a two-stage epipolar matching strategy using disjoint-set-union clustering and per-joint triangulation for multi-view multi-person 3D pose estimation in basketball.
-
SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
SUGAR turns diverse human videos into deployable humanoid loco-manipulation policies via automated prior extraction, physics refinement, and hierarchical distillation, showing scaling with data volume and zero-shot real-world transfer on six tasks.
-
EgoExo-WM: Unlocking Exo Video for Ego World Models
Method converts exocentric videos to egocentric format via body-pose extraction and kinematics to improve egocentric world-model prediction and planning.
-
Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
HA-HOI produces physically plausible 4D HOI animations from monocular videos by anchoring object reconstruction to human motion and refining the result in a physics-based humanoid-object simulator.
-
SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound
SAMe grounds complaints to organs, builds a lightweight patient anatomy model from one body image, and outputs probe initialization poses, outperforming keypoint baselines in real-robot liver and kidney trials.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
Pi-HOC: Pairwise 3D Human-Object Contact Estimation
Pi-HOC predicts dense 3D semantic contacts for all human-object pairs in an image via instance-aware tokens and an InteractionFormer, achieving higher accuracy and 20x throughput than prior methods.
-
RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild
RoSHI is a hybrid wearable that combines sparse IMUs and egocentric SLAM to capture accurate full-body 3D pose and shape data in natural environments for robot learning.
-
Duet: Dual-Robot Understanding via Efficient Teaching
DUET pretrains collaborative policies on human-human VR demonstrations then fine-tunes on minimal robot teleoperation data, achieving equal or better performance than robot-only baselines with 5.4x faster collection across four tasks.
-
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.
-
Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
Asset Harvester converts sparse in-the-wild object observations from AV driving logs into complete simulation-ready 3D assets via data curation, geometry-aware preprocessing, and a SparseViewDiT model that couples sparse-view multiview generation with 3D Gaussian lifting.
-
Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars
A minimal Gaussian splatting avatar pipeline using the Momentum Human Rig achieves the highest reported PSNR on PeopleSnapshot and ZJU-MoCap without learned deformations.
-
LUNA: Learning Universal 3D Human Animation Beyond Skinning
LUNA is an LBS-free neural animation model that maps 2D controls to 3D Gaussian deformations via a transformer motion regressor and hybrid supervision for realistic motion and zero-shot generalization.
-
SMART: SMPLest-X Mesh Adaptation and RAFT Tracking for Soccer Pose Estimation
SMART adapts SMPLest-X via stratified finetuning and RAFT tracking to achieve 0.647 validation and 0.593 test scores on the FIFA 2026 skeletal tracking challenge, versus baseline 1.053.