Rishabh Dabral
Scholar

Rishabh Dabral

Google Scholar ID: hLZNpkMAAAAJ
Max-Planck Institute for Informatics
Computer VisionDeep LearningHuman Pose Estimation
Citations & Impact
All-time
Citations
991
 
H-index
11
 
i10-index
13
 
Publications
20
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • Published papers:
  • 1. PractiLight: Practical Light Control Using Foundational Diffusion Models
  • 2. Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance
  • 3. Attention (as discrete-time Markov) Chains
  • 4. DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
  • 5. Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
  • 6. Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
  • 7. BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
  • 8. FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
  • 9. DUT: Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
  • 10. 3HANDS Dataset: Learning from Humans for Generating Naturalistic Handovers with Supernumerary Robotic Limbs
  • 11. Betsu-Betsu: Separable 3D Reconstruction of Two Interacting Objects from Multiple Views
  • 12. PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Research Experience
  • Started as a Research Group Leader at MPI for Informatics in August 2024; Also associated with the Research Training Group on Neuro-Explicit Models of Language, Vision, and Action at Saarland University.
Background
  • Research interests lie in the intersection of 3D computer vision, computer graphics, and multi-modal interactions. Particularly interested in developing algorithms for 3D human performance capture and synthesis.
Miscellany
  • Looking for outstanding PhD students to join the team.