27 citations · 66 across the 23 of their papers we have counts for
7 papers · 1 filter
Conditional Imaging for Privacy-Preserving Visual Sensing
Hengyu Lian, Debabrata Mandal, Anzhou Wen +3
Conventional visual sensing faces a fundamental dilemma: information that should remain private today may need to be recovered tomorrow. This challenge is becoming increasingly imp…
HoOPOE: A Holography-Optimized Perceptual ObjectivE function
Ethan Chen, Xi Peng, Alexandre Chapiro +6
Holographic devices must reconstruct an entire light field given a finite number of spatial light modulator (SLM) pixels, and must do so using scalar-wave diffraction from coherent…
EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation
Debabrata Mandal, Dongdong Fu, Jonathon Miller +3
Immersive displays can enable rich and diverse virtual experiences. Manually authoring every possible experience to realize this potential, however, is prohibitively expensive, dif…
Intrinsic Limitations of Single Layer Polychromatic Metalens for Virtual Reality Visors
Myunghoo Lee, Ben Nguyen, Zhihao Zhou +7
Virtual and augmented reality (VR/AR) visors require compact and lightweight optics. Metalenses have been widely proposed as ultrathin replacements for bulky refractive eyepieces,…
DeltaCam: Differential Intrinsic Camera Modeling for Video Generation
Debabrata Mandal, Zhihan Peng, Yujie Wang +1
Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance.…
Ellipsography: Single-Shot Speckle-Free Holography via Vectorial Interference Shaping
Anzhou Wen, Praneeth Chakravarthula
Holographic displays are widely regarded as the "ultimate" display technology, promising immersive 3D visuals with natural depth cues, continuous parallax, and perceptual realism.…
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
Debabrata Mandal, Soumitri Chattopadhyay, Yujie Wang +2
Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one re…