12 papers
OmniXRef: A Unified Framework for Multimodal Multi-Reference Video Editing
Xiaoyan Cong, Tianyu Wang, Hyeonho Jeong +7
Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), video references (e.g., camera…
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
Junyi Wu, Zekun Li, Chenhongyi Yang +9
Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual memory: the previously obse…
Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention
Zekun Li, Xiaoyan Cong, Hongyu Li +5
Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional n…
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Rahul Sajnani, Yulia Gryaditskaya, Radomír Měch +2
Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements…
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors
Xiaoyan Cong, Zekun Li, Zhiyang Dou +9
Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets…
PackUV: Packed Gaussian UV Maps for 4D Volumetric Video
Aashish Rai, Angela Xing, Anushka Agarwal +5
Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality re…
HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features
Arnab Dey, Cheng-You Lu, Andrew I. Comport +3
Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their…
MotionGlot: A Multi-Embodied Motion Generation Model
Sudarshan Harithas, Srinath Sridhar
This paper introduces MotionGlot, a model that can generate motion across multiple embodiments with different action dimensions, such as quadruped robots and human bodies. By lever…
EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos
Aashish Rai, Srinath Sridhar
We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric v…
GenHeld: Generating and Editing Handheld Objects
Chaerin Min, Srinath Sridhar
Grasping is an important human activity that has long been studied in robotics, computer vision, and cognitive science. Most existing works study grasping from the perspective of s…
GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields
Arnab Dey, Di Yang, Rohith Agaram +4
Recent advances in Neural Radiance Fields (NeRF) have demonstrated promising results in 3D scene representations, including 3D human representations. However, these representations…
GeoDiffuser: Geometry-Based Image Editing with Diffusion Models
Rahul Sajnani, Jeroen Vanbaar, Jie Min +2
The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are bespoke, imprecise, requir…